© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2566
    Prev
    Next
    INDEX
    Explanations

    Python-related terms and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to programming errors and exception handling in Python

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IDF
    -0.95
     Bris
    -0.93
     Sherman
    -0.91
     Kear
    -0.88
     Klein
    -0.86
    Lev
    -0.86
     Hert
    -0.85
     Herz
    -0.84
     Zionist
    -0.84
     Gallagher
    -0.83
    POSITIVE LOGITS
     python
    2.29
     Python
    2.15
    Python
    2.11
    python
    2.09
    py
    1.94
     py
    1.90
    ython
    1.85
     Py
    1.83
     pip
    1.78
    Py
    1.75
    Activations Density 0.162%

    No Known Activations