© 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. 3-RES-JB
    11. 18394
    Prev
    Next
    INDEX
    Explanations

    mentions of issues related to voting and elections

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voter issues and participation

    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
    Ļ½
    -0.83
    ahime
    -0.76
     Palestin
    -0.73
    Else
    -0.73
    eq
    -0.70
    obar
    -0.70
    eton
    -0.69
    ĸļ
    -0.68
    ensed
    -0.67
    estial
    -0.67
    POSITIVE LOGITS
     turnout
    1.06
     voter
    0.97
     registration
    0.92
     disenfranch
    0.86
     voting
    0.82
     ballots
    0.80
     votes
    0.79
     Voter
    0.78
     voters
    0.77
    eering
    0.75
    Activations Density 0.011%

    No Known Activations