© 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. 7-RES-JB
    11. 21458
    Prev
    Next
    INDEX
    Explanations

    details or statistics related to sporting events

    oai_token-act-pair · gpt-3.5-turbo

    statistical performance metrics in sports contexts

    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
     insign
    -0.69
    etus
    -0.68
    dor
    -0.68
    ITNESS
    -0.67
    helle
    -0.65
    hoe
    -0.65
     Fenrir
    -0.65
    atom
    -0.62
    agus
    -0.62
    phant
    -0.62
    POSITIVE LOGITS
     postseason
    0.97
     outings
    0.92
     consecutive
    0.90
     playoff
    0.88
     preseason
    0.87
     matchups
    0.87
     league
    0.86
     seasons
    0.85
     playoffs
    0.83
     offseason
    0.82
    Activations Density 0.229%

    No Known Activations