Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 24475
    Prev
    Next
    INDEX
    Explanations

    words related to voting and election processes

    oai_token-act-pair · gpt-3.5-turbo

    references to voting processes and mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.78
    Mount
    -0.74
     Palestin
    -0.73
    Else
    -0.71
    EMA
    -0.69
    £ı
    -0.68
    obar
    -0.68
    hester
    -0.68
    cele
    -0.66
    quite
    -0.66
    POSITIVE LOGITS
     voting
    1.32
     votes
    1.11
     ballots
    1.03
     Vote
    1.03
     vote
    1.03
     Voting
    0.97
    oting
    0.90
    vote
    0.86
     machines
    0.85
    eering
    0.85
    Activations Density 0.010%

    No Known Activations