© 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. 12-RES-JB
    11. 4016
    Prev
    Next
    INDEX
    Explanations

    names of sports teams, players, and coaches

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to coaches and teams in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     constitu
    -0.90
     NBA
    -0.80
     USL
    -0.77
     AHL
    -0.74
     OPEC
    -0.71
     NHL
    -0.71
     ECB
    -0.71
     Swan
    -0.68
    rha
    -0.67
    bledon
    -0.67
    POSITIVE LOGITS
     Baal
    0.78
    riots
    0.78
    ovie
    0.78
    aeper
    0.73
    Steel
    0.73
    erent
    0.73
     Ravens
    0.71
    Brown
    0.70
     sacked
    0.70
     Harbaugh
    0.70
    Activations Density 0.184%

    No Known Activations