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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10-RES-JB
    6. 8796
    Prev
    Next
    INDEX
    Explanations

    mentions of documents, reports, statements, and briefings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "on" that indicate topics or subjects being discussed

    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
    olla
    -0.74
    ï¸ı
    -0.69
    ographers
    -0.67
    EngineDebug
    -0.66
    rio
    -0.65
    AppData
    -0.65
    DERR
    -0.65
    ¨
    -0.64
    usercontent
    -0.63
    flies
    -0.62
    POSITIVE LOGITS
     behalf
    1.56
     how
    0.99
     why
    0.93
     topics
    0.89
     Wednesday
    0.88
     Tuesday
    0.83
     Monday
    0.83
    etime
    0.83
     Thursday
    0.83
     Aging
    0.82
    Activations Density 0.181%

    No Known Activations