© 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. 9-RES-JB
    11. 2841
    Prev
    Next
    INDEX
    Explanations

    owner, editor, professor, director, maker, leader, commander, Republican, creator, chairman, author

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles associated with leadership or ownership in various contexts

    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
    article
    -0.56
    articles
    -0.55
    osi
    -0.55
    sylv
    -0.54
    asive
    -0.54
    {"
    -0.53
    kos
    -0.53
     Bros
    -0.53
    idency
    -0.52
    ":[{"
    -0.52
    POSITIVE LOGITS
     extraord
    1.05
     emer
    1.01
    uably
    0.89
    director
    0.80
     director
    0.75
    founder
    0.71
     curator
    0.69
     of
    0.68
    quartered
    0.67
    manager
    0.66
    Activations Density 0.156%

    No Known Activations