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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10952
    Prev
    Next
    INDEX
    Explanations

    references to legislation and political acts, particularly related to voting rights

    oai_token-act-pair · gpt-3.5-turbo

    references to voting rights and related concepts

    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
    ologically
    -0.78
    Else
    -0.75
    peria
    -0.75
     tremend
    -0.74
     Palestin
    -0.73
    olog
    -0.72
    ĸļ
    -0.71
    ology
    -0.71
    ãĤ¨ãĥ«
    -0.69
    Mount
    -0.69
    POSITIVE LOGITS
     voting
    1.08
     votes
    0.93
    eering
    0.93
     ballots
    0.92
     vote
    0.92
     machines
    0.91
     Vote
    0.83
    oting
    0.83
    ricting
    0.82
     Voting
    0.80
    Activations Density 0.011%

    No Known Activations