© 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. 14978
    Prev
    Next
    INDEX
    Explanations

    programming terms and instructions

    oai_token-act-pair · gpt-3.5-turbo

    elements of programming or coding syntax

    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
    orne
    -0.72
    Woman
    -0.67
    ŃĶ
    -0.66
    Thirty
    -0.63
    usky
    -0.62
    mie
    -0.61
    ogie
    -0.61
    IU
    -0.60
    Girls
    -0.60
    intend
    -0.60
    POSITIVE LOGITS
     eg
    1.17
     optionally
    1.16
     namely
    1.11
     ie
    1.09
     hence
    1.02
     thus
    0.95
     specifying
    0.94
     whereas
    0.94
     e
    0.93
     ~/.
    0.91
    Activations Density 0.206%

    No Known Activations