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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 879
    Prev
    Next
    INDEX
    Explanations

    legislation or legal-related terms and descriptions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of legislative actions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´
    -0.70
     ¯
    -0.69
    stery
    -0.66
    direction
    -0.65
     Guru
    -0.64
     Faw
    -0.64
     TMZ
    -0.63
    dad
    -0.62
    gery
    -0.61
    actly
    -0.60
    POSITIVE LOGITS
     respective
    1.15
     economies
    1.08
     respectively
    1.02
     legislatures
    1.02
     populations
    1.01
     implementing
    0.97
     nationals
    0.97
     acad
    0.95
     democracies
    0.94
     collectively
    0.92
    Activations Density 0.507%

    No Known Activations