© 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. 9-RES-JB
    11. 2289
    Prev
    Next
    INDEX
    Explanations

    reports or studies about specific topics or fields

    oai_token-act-pair · gpt-3.5-turbo

    references to new reports or studies

    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
    respective
    -0.81
    agree
    -0.77
    ufact
    -0.73
    ouse
    -0.72
    urations
    -0.72
    Zip
    -0.72
    usercontent
    -0.71
     actionGroup
    -0.69
    cius
    -0.69
    DERR
    -0.68
    POSITIVE LOGITS
    bie
    1.10
    foundland
    0.94
     YORK
    0.92
     batch
    0.90
     documentary
    0.89
     edition
    0.88
     spate
    0.84
     study
    0.84
     Zealand
    0.84
     testament
    0.83
    Activations Density 0.090%

    No Known Activations