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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 10316
    Prev
    Next
    INDEX
    Explanations

    warnings or advice given in text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and expressions of caution or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pires
    -0.85
    izable
    -0.63
    itud
    -0.62
     disparate
    -0.62
     differed
    -0.57
     matched
    -0.57
     contrasts
    -0.57
     progressed
    -0.56
     paralle
    -0.56
     manifested
    -0.56
    POSITIVE LOGITS
     Otherwise
    1.19
    Otherwise
    0.99
     lest
    0.98
    unless
    0.95
     THEY
    0.89
     Especially
    0.88
     otherwise
    0.88
     Seriously
    0.85
    Unless
    0.85
    because
    0.83
    Activations Density 0.400%

    No Known Activations