© 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 EvalsExportsAPI 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. 20708
    Prev
    Next
    INDEX
    Explanations

    mentions or references to sports teams, particularly the Cincinnati Bengals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Cincinnati Bengals football team

    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
     Lauder
    -0.75
    uable
    -0.72
    uckland
    -0.72
    bes
    -0.71
    eting
    -0.71
    downs
    -0.71
    tub
    -0.70
    ter
    -0.70
    down
    -0.69
    rooms
    -0.69
    POSITIVE LOGITS
     Bengals
    1.00
    incinn
    0.99
    ĸļ
    0.95
     Reds
    0.89
     Bengal
    0.80
    incinnati
    0.77
    ļéĨĴ
    0.74
    hurst
    0.73
    hester
    0.70
    endish
    0.70
    Activations Density 0.103%

    No Known Activations