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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22587
    Prev
    Next
    INDEX
    Explanations

    words related to medical procedures or anatomical structures, specifically focusing on the colon

    oai_token-act-pair · gpt-3.5-turbo

    references to colon and related medical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.76
    isSpecialOrderable
    -0.75
    IELD
    -0.73
    Downloadha
    -0.72
    NESS
    -0.71
    natureconservancy
    -0.70
    GET
    -0.70
    ILLE
    -0.68
    ITH
    -0.67
    displayText
    -0.66
    POSITIVE LOGITS
     colon
    1.00
     Colon
    0.98
    osc
    0.92
    izers
    0.87
    vier
    0.84
    esses
    0.79
    itus
    0.77
    esis
    0.77
    ophon
    0.77
    ess
    0.76
    Activations Density 0.009%

    No Known Activations