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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 18472
    Prev
    Next
    INDEX
    Explanations

    trying to identify festive occasions or holidays

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "rule" or "regulation."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.82
    rast
    -0.77
    POL
    -0.69
    rypt
    -0.69
    itutional
    -0.68
    chrom
    -0.66
    soDeliveryDate
    -0.64
    anced
    -0.63
    ãĥ¯ãĥ³
    -0.62
    romeda
    -0.62
    POSITIVE LOGITS
    clips
    0.87
    cules
    0.83
    ¶æ
    0.76
    nown
    0.75
    iffe
    0.73
    ule
    0.73
    mers
    0.73
    ttle
    0.72
    ffe
    0.71
    lect
    0.71
    Activations Density 0.075%

    No Known Activations