Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15786
    Prev
    Next
    INDEX
    Explanations

    references to a person named "Cohen" in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cohen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reluct
    -0.76
    oppable
    -0.76
    rha
    -0.75
    ICAN
    -0.73
    mingham
    -0.68
    tub
    -0.68
    retched
    -0.64
    atical
    -0.64
    anamo
    -0.64
    stood
    -0.63
    POSITIVE LOGITS
    agher
    0.95
    ²¾
    0.92
    bach
    0.82
     Strauss
    0.71
    rosso
    0.71
    lette
    0.70
    Desk
    0.69
    SHIP
    0.66
    ¬¼
    0.66
    wald
    0.66
    Activations Density 0.023%

    No Known Activations