Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 23579
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Congress"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Congress."

    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
     MM
    -0.70
     srf
    -0.65
    imilar
    -0.63
     Britann
    -0.63
     Fatal
    -0.62
     999
    -0.62
     Nanto
    -0.61
     McA
    -0.61
     Sussex
    -0.61
    âķIJâķIJ
    -0.61
    POSITIVE LOGITS
    woman
    1.17
    ional
    1.06
    crit
    0.91
     appropriated
    0.83
     Congress
    0.83
    ername
    0.83
    men
    0.81
    arians
    0.78
    member
    0.77
     appropriations
    0.77
    Activations Density 0.017%

    No Known Activations