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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11088
    Prev
    Next
    INDEX
    Explanations

    mentions of appearances in sports games

    oai_token-act-pair · gpt-3.5-turbo

    mentions of player appearances and statistics in sports contexts

    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
    sonian
    -0.64
     currents
    -0.61
    TRUMP
    -0.59
    hai
    -0.58
    laws
    -0.58
    cul
    -0.57
     Parkinson
    -0.56
    Hi
    -0.55
    Exit
    -0.55
     personalities
    -0.55
    POSITIVE LOGITS
     sparing
    1.02
     colleg
    0.81
     fullback
    0.73
    unte
    0.72
     fewer
    0.70
    seven
    0.69
     stint
    0.68
     pivotal
    0.68
    omore
    0.68
     unused
    0.67
    Activations Density 0.141%

    No Known Activations