© 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. 21189
    Prev
    Next
    INDEX
    Explanations

    phrases indicating support or fundraising calls

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to support and donations

    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
    auc
    -0.75
    acci
    -0.72
    cffffcc
    -0.69
    enegger
    -0.69
    locks
    -0.66
    away
    -0.63
    eneg
    -0.60
    inis
    -0.60
    eners
    -0.60
    illion
    -0.59
    POSITIVE LOGITS
    Independent
    0.86
     Examiner
    0.77
    independent
    0.75
     LW
    0.73
     Marketplace
    0.73
    ¥µ
    0.71
     Voices
    0.69
     Journalism
    0.68
     Us
    0.67
     Tablet
    0.67
    Activations Density 0.049%

    No Known Activations