© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 147
    Prev
    Next
    INDEX
    Explanations

    words related to political elections

    oai_token-act-pair · gpt-3.5-turbo

    references to midterm elections and related political events

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

    No Comments

    Negative Logits
    pots
    -0.92
    ijk
    -0.81
    pot
    -0.77
    orld
    -0.76
    resp
    -0.74
    tics
    -0.70
     Spit
    -0.70
    rosis
    -0.70
    king
    -0.69
    ether
    -0.68
    POSITIVE LOGITS
     midterm
    1.00
     elections
    0.99
     election
    0.89
     Election
    0.85
    é¾įå¥ij士
    0.81
     slump
    0.79
     tightening
    0.77
     elector
    0.77
     reelection
    0.77
     electorate
    0.76
    Activations Density 0.007%

    No Known Activations