© 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. 10-RES-JB
    11. 17447
    Prev
    Next
    INDEX
    Explanations

    instructions or explanations on how something works

    oai_token-act-pair · gpt-3.5-turbo

    explanations or descriptions of how things function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij士
    -0.83
    gur
    -0.70
    livion
    -0.69
    BuyableInstoreAndOnline
    -0.66
     Dwell
    -0.65
    mson
    -0.64
    imar
    -0.64
    xit
    -0.63
    hawks
    -0.62
    ĪĴ
    -0.62
    POSITIVE LOGITS
     differently
    0.83
     versus
    0.78
     internally
    0.76
     differs
    0.75
     mechanically
    0.74
     together
    0.73
    atically
    0.73
     collabor
    0.72
    advertisement
    0.71
    together
    0.69
    Activations Density 0.060%

    No Known Activations