© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 9621
    Prev
    Next
    INDEX
    Explanations

    mentions of legal rules and regulations, specifically ordinances

    oai_token-act-pair · gpt-3.5-turbo

    references to specific local regulations or laws

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

    No Comments

    Negative Logits
    stocks
    -0.86
    cro
    -0.73
     Lanka
    -0.73
    oyal
    -0.72
    vae
    -0.72
    espie
    -0.70
    playing
    -0.70
    itaire
    -0.70
    kies
    -0.68
    pathy
    -0.68
    POSITIVE LOGITS
     ordinance
    1.00
     ordinances
    1.00
    inances
    0.95
     enforcement
    0.94
    inarily
    0.84
     prohibiting
    0.84
     enacted
    0.82
     violations
    0.82
     authorizing
    0.80
    uary
    0.78
    Activations Density 0.008%

    No Known Activations