© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 13746
    Prev
    Next
    INDEX
    Explanations

    references to American football players, particularly wide receivers

    oai_token-act-pair · gpt-3.5-turbo

    references to wide receivers in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iewicz
    -0.89
     plur
    -0.80
    xit
    -0.77
    henko
    -0.74
    naires
    -0.72
    arist
    -0.70
    uca
    -0.70
    ement
    -0.70
    ename
    -0.69
    ilingual
    -0.68
    POSITIVE LOGITS
     Receiver
    0.94
     receiver
    0.91
     receptions
    0.86
     touchdowns
    0.85
     receivers
    0.84
     corps
    0.80
    ceiver
    0.78
     touchdown
    0.77
     coach
    0.74
     cornerback
    0.73
    Activations Density 0.053%

    No Known Activations