© 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. 4-RES-JB
    11. 14848
    Prev
    Next
    INDEX
    Explanations

    measurements, such as distances and sizes, in various units

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measures and units of measurement

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

    No Comments

    Negative Logits
    raise
    -0.66
    eer
    -0.65
    apego
    -0.63
     Levin
    -0.62
     excellence
    -0.62
    Online
    -0.62
    bred
    -0.61
    lished
    -0.61
     Classics
    -0.60
    olini
    -0.60
    POSITIVE LOGITS
     apiece
    0.88
     diameter
    0.79
     sq
    0.78
     (~
    0.78
     increments
    0.78
     km
    0.73
    poons
    0.73
    renheit
    0.72
    mb
    0.72
     cubic
    0.72
    Activations Density 0.133%

    No Known Activations