© 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. 12-RES-JB
    11. 4872
    Prev
    Next
    INDEX
    Explanations

    numerical values related to quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases and words related to quantities and amounts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    selves
    -0.69
    ullivan
    -0.65
    asts
    -0.62
    liction
    -0.56
     Borders
    -0.56
    ades
    -0.54
    aldi
    -0.53
    warts
    -0.53
    vision
    -0.52
    swick
    -0.52
    POSITIVE LOGITS
     spent
    0.92
     of
    0.86
     invested
    0.86
     expended
    0.85
     ingested
    0.82
     deducted
    0.76
    ngth
    0.76
     owed
    0.75
     consumed
    0.71
     allotted
    0.70
    Activations Density 0.053%

    No Known Activations