© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 12145
    Prev
    Next
    INDEX
    Explanations

    terms related to voting, registration, and fraud

    oai_token-act-pair · gpt-3.5-turbo

    references to voters and voting-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shack
    -0.77
    bane
    -0.74
     Kinnikuman
    -0.68
    arts
    -0.64
    bars
    -0.64
     Stra
    -0.63
     Bars
    -0.62
    uo
    -0.61
     xx
    -0.61
     Crate
    -0.61
    POSITIVE LOGITS
     voter
    3.68
     Voter
    3.00
     Voters
    2.18
     voters
    2.07
     Voting
    2.03
     voting
    2.02
     elector
    1.98
     ballot
    1.93
     electoral
    1.70
     ballots
    1.69
    Activations Density 0.009%

    No Known Activations