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

    Neuronpedia

    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. 20579
    Prev
    Next
    INDEX
    Explanations

    phrases related to critiques, reviews, and responses to reported information

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal and regulatory issues

    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
    $.
    -0.75
    unless
    -0.71
    >.
    -0.70
    +.
    -0.67
    cause
    -0.66
    .?
    -0.66
    ().
    -0.65
    .''.
    -0.64
    %.
    -0.64
     '.
    -0.62
    POSITIVE LOGITS
    ,[
    0.84
    ,
    0.80
     (),
    0.77
    *,
    0.71
    ,,
    0.69
    Downloadha
    0.68
     ,
    0.65
    ?,
    0.64
     foregoing
    0.63
    ®,
    0.63
    Activations Density 0.764%

    No Known Activations