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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 15254
    Prev
    Next
    INDEX
    Explanations

    medical facilities and procedures

    oai_token-act-pair · gpt-3.5-turbo

    social issues and health-related crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pard
    -0.59
    exclusive
    -0.59
    én
    -0.58
    product
    -0.57
    ':
    -0.56
    olitics
    -0.55
    ccording
    -0.54
    \":
    -0.54
     BALL
    -0.53
    ãĤ¢ãĥ«
    -0.53
    POSITIVE LOGITS
     etc
    1.20
    ,...
    0.92
    ?,
    0.86
     ect
    0.76
    !,
    0.74
    ,,
    0.69
    /,
    0.69
     (),
    0.68
     respectively
    0.68
    (),
    0.67
    Activations Density 1.081%

    No Known Activations