© 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. 13345
    Prev
    Next
    INDEX
    Explanations

    mentions of UFC events

    oai_token-act-pair · gpt-3.5-turbo

    references to UFC events and related terminology

    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
    tz
    -0.69
     Cthulhu
    -0.66
     VW
    -0.64
     Pelosi
    -0.63
     Wynne
    -0.63
     Samar
    -0.63
    PsyNetMessage
    -0.63
    cially
    -0.62
    âĹ¼
    -0.62
    Tesla
    -0.62
    POSITIVE LOGITS
     Fight
    1.13
     FIGHT
    0.97
     Fighter
    0.91
     189
    0.90
     heavyweight
    0.90
     182
    0.89
     196
    0.88
    UFC
    0.87
     217
    0.87
     193
    0.87
    Activations Density 0.038%

    No Known Activations