© 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. 20991
    Prev
    Next
    INDEX
    Explanations

    specific references to sports events, teams, and scores

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and its variations to indicate key subjects or themes

    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
    enegger
    -1.10
    EVA
    -0.90
    illion
    -0.82
    cone
    -0.82
    soType
    -0.78
    ãĤ¢ãĥ«
    -0.77
    soDeliveryDate
    -0.77
    adata
    -0.76
    Attorney
    -0.75
    obyl
    -0.75
    POSITIVE LOGITS
     Bulldogs
    1.17
     Tigers
    1.12
     Wildcats
    1.12
     Jackets
    1.11
     Cats
    1.08
     Hornets
    1.02
     Bears
    1.01
     Hawks
    1.00
     Spartans
    1.00
     matchup
    0.99
    Activations Density 0.131%

    No Known Activations