Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20666
    Prev
    Next
    INDEX
    Explanations

    references to Formula racing series, specifically Formula 9 and Formula 8

    oai_token-act-pair · gpt-3.5-turbo

    references to Formula racing series and their specific events or categories

    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
    asin
    -0.76
    asking
    -0.70
    fully
    -0.69
    asio
    -0.69
    ym
    -0.68
    heres
    -0.68
    holder
    -0.67
    gow
    -0.67
    itory
    -0.66
    erv
    -0.65
    POSITIVE LOGITS
    ĩ
    0.84
     Drift
    0.84
    ī
    0.78
     XIV
    0.75
     One
    0.73
    Python
    0.72
    ĺ
    0.71
    ĥ
    0.71
    ĭ
    0.68
     Eleven
    0.66
    Activations Density 0.051%

    No Known Activations