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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12517
    Prev
    Next
    INDEX
    Explanations

    mentions of political processes and activities, particularly related to parliamentary sessions and legislative procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legislative processes and parliamentary actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.74
     marketed
    -0.71
    uilt
    -0.70
    axter
    -0.69
    zsche
    -0.65
    odka
    -0.64
    çīĪ
    -0.64
     Glac
    -0.63
     compan
    -0.62
    resp
    -0.62
    POSITIVE LOGITS
     adjourn
    1.12
     votes
    1.11
     filibuster
    1.06
     hearings
    1.03
     Speaker
    1.03
     recess
    1.02
    vote
    1.01
     vote
    1.01
     session
    1.00
     elections
    0.99
    Activations Density 0.143%

    No Known Activations