© 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. 11-RES-JB
    11. 6003
    Prev
    Next
    INDEX
    Explanations

    technical or complex concepts that require explaining or justification

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating the existence or nature of an issue or situation

    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
    ventures
    -0.68
    stad
    -0.67
    Tonight
    -0.66
    agues
    -0.64
    æ³
    -0.64
     Authors
    -0.62
    Others
    -0.60
    Hours
    -0.59
    illions
    -0.59
    uggets
    -0.57
    POSITIVE LOGITS
     that
    1.10
     undoubtedly
    0.91
     namely
    0.90
    that
    0.90
     ensuring
    0.88
     THAT
    0.87
     figuring
    0.82
     how
    0.82
     consistency
    0.77
     whether
    0.77
    Activations Density 0.113%

    No Known Activations