© 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. 9-RES-JB
    11. 4190
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation and formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ply
    -0.74
    rie
    -0.71
     Jinn
    -0.68
    kefeller
    -0.67
    ries
    -0.66
    rived
    -0.66
    uchin
    -0.66
    leigh
    -0.65
    rell
    -0.64
    leneck
    -0.64
    POSITIVE LOGITS
     Archdemon
    1.03
    AM
    0.99
     AM
    0.99
     Amar
    0.98
     AU
    0.96
    AU
    0.95
     Ap
    0.95
     AV
    0.94
    AC
    0.94
    AE
    0.94
    Activations Density 0.762%

    No Known Activations