© 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. 2-RES-JB
    11. 22569
    Prev
    Next
    INDEX
    Explanations

    mentions of reports and investigations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "report."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.90
    cffff
    -0.76
    othing
    -0.75
     Klux
    -0.69
     stead
    -0.65
    conservancy
    -0.65
     plaster
    -0.64
    venge
    -0.63
    JV
    -0.63
     notor
    -0.62
    POSITIVE LOGITS
    report
    0.95
    books
    0.91
    Report
    0.83
    Crash
    0.83
     report
    0.82
     reports
    0.81
    ufact
    0.72
    imony
    0.71
    Reporting
    0.69
    book
    0.68
    Activations Density 0.048%

    No Known Activations