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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1065
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific names and entities, especially those involving Dominique Strauss-Kahn and Levi

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names associated with high-profile individuals and entities

    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
    perse
    -0.76
    here
    -0.75
    board
    -0.75
    boards
    -0.74
    itions
    -0.74
    borgh
    -0.73
    apolis
    -0.73
    oran
    -0.73
    nces
    -0.73
    rill
    -0.73
    POSITIVE LOGITS
     Strauss
    1.44
     Zel
    0.70
    tera
    0.66
    bard
    0.63
     Schmidt
    0.63
    hei
    0.63
     chord
    0.63
     congr
    0.62
    059
    0.62
    KI
    0.61
    Activations Density 0.025%

    No Known Activations