© 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. 9-RES-JB
    11. 24297
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters, specifically those related to lawsuits and justice

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "vest" and similar phonetic patterns

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     envy
    -0.70
    OPA
    -0.63
    ADRA
    -0.62
     trillions
    -0.60
     contrace
    -0.59
     aloud
    -0.59
    γ
    -0.59
     variance
    -0.58
     bog
    -0.56
    REAM
    -0.56
    POSITIVE LOGITS
    ï¸ı
    1.02
    velt
    0.87
    merce
    0.80
    schild
    0.74
    ebook
    0.71
    monary
    0.71
    avid
    0.70
    claw
    0.70
    inary
    0.69
    aiden
    0.68
    Activations Density 0.220%

    No Known Activations