© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1115
    Prev
    Next
    INDEX
    Explanations

    programming code snippets related to strings and iterators

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming and coding syntax

    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
    quickShipAvailable
    -0.83
    uador
    -0.79
    ascript
    -0.78
    icio
    -0.72
    estival
    -0.72
    govtrack
    -0.71
    orsi
    -0.70
    ulence
    -0.69
    ento
    -0.68
    love
    -0.67
    POSITIVE LOGITS
     buf
    0.87
     ptr
    0.79
     buffer
    0.73
    buf
    0.73
    ();
    0.73
    pend
    0.73
     padd
    0.71
    ptr
    0.71
     sizeof
    0.70
     __
    0.69
    Activations Density 0.048%

    No Known Activations