© 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. 14267
    Prev
    Next
    INDEX
    Explanations

    financial and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas and periods, signaling their frequency in the document

    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
    Parameter
    -0.78
    elta
    -0.75
    ELD
    -0.74
    eston
    -0.74
    ,[
    -0.73
    Catalog
    -0.72
    MSN
    -0.70
    Font
    -0.69
    coat
    -0.69
    Next
    -0.69
    POSITIVE LOGITS
     unless
    0.88
     uh
    0.80
     nonexistent
    0.78
     wherever
    0.75
     namely
    0.75
     whichever
    0.75
     whoever
    0.74
     excluding
    0.74
     beware
    0.73
     whenever
    0.73
    Activations Density 0.110%

    No Known Activations