© 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. 3-RES-JB
    11. 1745
    Prev
    Next
    INDEX
    Explanations

    mentions of political elections

    oai_token-act-pair · gpt-3.5-turbo

    mentions of elections

    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
    osis
    -0.82
    Property
    -0.72
    Reason
    -0.69
    Factor
    -0.66
    uran
    -0.66
    Reloaded
    -0.65
    Else
    -0.64
    ty
    -0.63
    ijk
    -0.63
    Family
    -0.62
    POSITIVE LOGITS
    eering
    1.34
     polls
    0.98
     elections
    0.95
     polling
    0.92
     committees
    0.84
    ricting
    0.81
     ballots
    0.80
    eer
    0.80
     Elections
    0.80
    eers
    0.79
    Activations Density 0.013%

    No Known Activations