© 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. 9-RES-JB
    11. 18615
    Prev
    Next
    INDEX
    Explanations

    the name "McCain."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of John McCain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MW
    -0.73
    hops
    -0.65
    heet
    -0.64
    bidden
    -0.64
    OX
    -0.62
     Peb
    -0.62
     Pixie
    -0.61
    liga
    -0.61
     Drift
    -0.60
    uristic
    -0.60
    POSITIVE LOGITS
    artney
    0.97
     McCain
    0.91
    iband
    0.79
     pard
    0.75
     Caucus
    0.74
     aide
    0.71
     vetoed
    0.70
    patrick
    0.69
    Collins
    0.68
     ç¥ŀ
    0.65
    Activations Density 0.037%

    No Known Activations