clip-dissect

clip-dissect is a skill for Claude Code from zjunlp/Mechanist. It costs 76 tokens per session (5,526 once invoked), scanned A, original, MIT.

A tool for automatically describing what individual neurons in deep vision models respond to, using CLIP-based comparisons. CLIP is a model that relates images and text.

In plain words
What is it for?
Use it to analyze neurons in CNNs and vision transformers, compare descriptions with methods such as NetDissect or MILAN, and test concepts using image datasets such as Broden or ImageNet.
Why use it?
It helps researchers understand visual model internals instead of seeing only the model’s final class prediction.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mechanist plugin — 54 skills, 4 agents shipped together

Good fit Use it to analyze neurons in CNNs and vision transformers, compare descriptions with methods such as NetDissect or MILAN, and test concepts using image datasets such as Broden or ImageNet.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zjunlp/mechanist/clip-dissect
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add zjunlp/Mechanist --skill clip-dissect
Clone the repo
git clone --depth 1 https://github.com/zjunlp/Mechanist

Made for: Claude Code.

Or install mechanist, the plugin that ships this one along with the rest of its 54 skills, 4 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for clip-dissect

README.md
[![agentmods](https://agentmods.dev/badge/skills/zjunlp/mechanist/clip-dissect.svg)](https://agentmods.dev/skills/zjunlp/mechanist/clip-dissect)
Your own site
<a href="https://agentmods.dev/skills/zjunlp/mechanist/clip-dissect"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/clip-dissect.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,526 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.05526
Opus 5 $0.00038 $0.02763
Sonnet 5 $0.00015 $0.01105
Haiku 4.5 $0.00008 $0.00553

Measured 8d ago against content hash 550ed295c1de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

clip-dissect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run_clip_dissect.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/mechanism-skills/multi-modal/clip-dissect/SKILL.md · 641 lines

How it starts

The opening of the file, as written. The whole thing — 641 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLIP-Dissect Skill

When to Use

Activate this skill when:

  • You need to automatically describe what individual neurons in a deep vision network respond to
  • You are performing mechanistic interpretability or explainable AI research on CNNs or Vision Transformers
  • You want to understand neuron-level representations in models like ResNet-50, ResNet-18, ViT, or custom models
  • You need to compare neuron descriptions against baselines like NetDissect or MILAN
  • You want to probe neural network layers using a concept set (e.g., 3k, 10k, 20k English words)
  • You are working with Broden or ImageNet as a probing dataset
  • You need to evaluate how well neuron descriptions predict class-level behavior in a model
  • Keywords: neuron dissection, CLIP, neural network interpretability, concept-based explanations, network dissection, probe dataset, activation analysis, feature visualization

Quick Reference


Installation / Setup

Prerequisites

  • Python 3.10
  • PyTorch >= 1.12.0 (also compatible with 2.0), Torchvision >= 0.13
  • CUDA-compatible GPU recommended (CPU inference supported)

Step-by-Step Installation

# Step 1: Clone the repository
git clone https://github.com/Trustworthy-ML-Lab/CLIP-dissect.git
cd CLIP-dissect

# Step 2: Install Python 3.10 (if not already installed)
# Using conda:
conda create -n clip_dissect python=3.10
conda activate clip_dissect

# Step 3: Install PyTorch and Torchvision (tested with 1.12.0, also works with 2.0)
# Visit https://pytorch.org/get-started/previous-versions/ for exact commands.
# Example for CUDA 11.3:
pip install torch==1.12.0+cu113 torchvision==0.13.0+cu113 --extra-index-url https://download.pytorch.org/whl/cu113

# Step 4: Install remaining dependencies
pip install -r requirements.txt

# Step 5: Download the Broden dataset (images only)
bash dlbroden.sh

# Step 6 (Optional): Download ResNet-18 pretrained on Places-365
bash dlzoo_example.sh

Read the full file on GitHub · 641 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 641 lines · 76 tokens per session scan A 550ed295c1de

Subscribe to this mod's changes

clip-dissect is a skill published in the GitHub repository zjunlp/Mechanist (72 stars, last pushed 12d ago), licensed MIT. It adds 76 tokens to every session and 5,526 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.