© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RES-JB
    11. 14142
    Prev
    Next
    INDEX
    Explanations

    information related to financial or economic activities

    oai_token-act-pair · gpt-3.5-turbo

    patterns of special characters or symbols in written content

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     shelf
    -0.81
     Glacier
    -0.75
    ©¶æ
    -0.65
     charm
    -0.65
     Polar
    -0.64
     slab
    -0.64
     Kard
    -0.63
    agall
    -0.63
     Slug
    -0.63
     derby
    -0.61
    POSITIVE LOGITS
    cause
    1.06
    especially
    0.95
    according
    0.94
    then
    0.89
    said
    0.88
    particularly
    0.88
    sure
    0.86
    which
    0.84
    dating
    0.84
    _>
    0.82
    Activations Density 0.194%

    No Known Activations