© 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. 11-RES-JB
    11. 1540
    Prev
    Next
    INDEX
    Explanations

    occurrences of sports-related events, specifically goals scored in NHL games

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to first achievements in sports or careers

    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
    bara
    -0.90
     frameworks
    -0.80
    models
    -0.78
    projects
    -0.77
    papers
    -0.77
     Parties
    -0.75
    urrencies
    -0.75
    markets
    -0.73
    apters
    -0.72
    holes
    -0.72
    POSITIVE LOGITS
     appearance
    0.99
     consecutive
    0.98
     career
    0.96
     victory
    0.94
     straight
    0.90
     win
    0.89
     collegiate
    0.85
     outing
    0.80
     successive
    0.79
     homer
    0.78
    Activations Density 0.071%

    No Known Activations