© 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. 7-RES-JB
    11. 2277
    Prev
    Next
    INDEX
    Explanations

    phrases related to boxing matches and fighters

    oai_token-act-pair · gpt-3.5-turbo

    boxing-related terms and events, particularly those involving titles and matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quist
    -0.83
    Newsletter
    -0.77
    ulhu
    -0.77
     Helpful
    -0.75
    ophysical
    -0.74
    uckland
    -0.69
    ffect
    -0.69
    sted
    -0.66
    wagen
    -0.66
    ridges
    -0.66
    POSITIVE LOGITS
     bout
    0.99
     bouts
    0.95
     rematch
    0.93
     stopp
    0.91
     MMA
    0.86
     TBA
    0.80
    weights
    0.77
     wrestlers
    0.76
     championship
    0.75
     debut
    0.75
    Activations Density 0.121%

    No Known Activations