© 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. 3-RES-JB
    11. 17339
    Prev
    Next
    INDEX
    Explanations

    legal terms and courtroom-related language

    oai_token-act-pair · gpt-3.5-turbo

    judicial rulings and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icrobial
    -0.75
    icro
    -0.74
    ongh
    -0.73
    roleum
    -0.70
    ohyd
    -0.70
     livest
    -0.68
     airst
    -0.67
     sulph
    -0.67
    udeau
    -0.67
     neighbours
    -0.66
    POSITIVE LOGITS
    sup
    0.96
    iffs
    0.92
    Judge
    0.90
     rulings
    0.88
     Scalia
    0.87
    Sup
    0.85
    iff
    0.79
     justices
    0.79
     briefs
    0.77
     Judge
    0.76
    Activations Density 0.112%

    No Known Activations