© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23095
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States House of Representatives

    oai_token-act-pair · gpt-3.5-turbo

    references to the House of Representatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zsche
    -0.87
    ilitary
    -0.76
    vier
    -0.68
    ï¸ı
    -0.67
    oshop
    -0.66
    arre
    -0.64
    olean
    -0.63
    itars
    -0.62
    istically
    -0.62
    ocent
    -0.62
    POSITIVE LOGITS
     Speaker
    1.12
     Judiciary
    1.10
     Appropriations
    0.98
     Oversight
    0.96
    wives
    0.96
     GOP
    0.95
     Ways
    0.94
     Majority
    0.93
     Republicans
    0.89
    wife
    0.85
    Activations Density 0.039%

    No Known Activations