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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1230
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of elections

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "elections"

    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
     pad
    -0.74
    amen
    -0.69
     Shack
    -0.65
    reci
    -0.65
    layer
    -0.65
    vec
    -0.64
     Rap
    -0.63
     Monster
    -0.62
    uin
    -0.62
     Loft
    -0.60
    POSITIVE LOGITS
     elections
    3.66
     Elections
    2.83
     election
    2.41
     Election
    2.10
    election
    1.99
     electoral
    1.92
     polls
    1.91
     electing
    1.66
     ballots
    1.64
     voting
    1.58
    Activations Density 0.010%

    No Known Activations