© 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. 4-RES-JB
    11. 14861
    Prev
    Next
    INDEX
    Explanations

    mentions of the American political party "Congress"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Congress party

    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
     Conway
    -0.74
     srf
    -0.73
    ĵĺ
    -0.67
     Sussex
    -0.63
     Grimm
    -0.62
     Wembley
    -0.62
     Schne
    -0.61
    --+
    -0.61
     DW
    -0.60
     Gerr
    -0.60
    POSITIVE LOGITS
    woman
    1.09
    eers
    1.01
    ional
    0.98
    men
    0.95
    escent
    0.88
    crit
    0.85
    eer
    0.79
    women
    0.79
    bourg
    0.78
    ioned
    0.77
    Activations Density 0.017%

    No Known Activations