© 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. 15026
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "No." followed by a number likely indicating a ranking or order

    oai_token-act-pair · gpt-3.5-turbo

    rankings related to player performance and statistics

    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
    theless
    -0.76
    staking
    -0.70
     suppressed
    -0.61
     totality
    -0.58
     eleph
    -0.58
     enthus
    -0.57
    redits
    -0.56
    EStreamFrame
    -0.56
     muted
    -0.54
     insecure
    -0.53
    POSITIVE LOGITS
    isy
    0.85
    .–
    0.82
    .
    0.78
    Va
    0.77
    .?
    0.74
    xious
    0.74
    .,
    0.72
    Sleep
    0.72
    SQL
    0.70
    Ops
    0.70
    Activations Density 0.019%

    No Known Activations