© 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. 9-RES-JB
    11. 13190
    Prev
    Next
    INDEX
    Explanations

    mentions of sports plays and game events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports scoring events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anmar
    -0.78
    ngth
    -0.71
    jriwal
    -0.69
    enegger
    -0.67
    insula
    -0.67
     cav
    -0.65
    ortment
    -0.61
     diligence
    -0.61
     unemploy
    -0.61
    agents
    -0.60
    POSITIVE LOGITS
     halftime
    0.90
     clin
    0.88
     unanswered
    0.82
     insur
    0.78
     concede
    0.76
    goal
    0.75
    Winner
    0.74
     conceded
    0.74
     clinch
    0.70
     scoreboard
    0.70
    Activations Density 0.253%

    No Known Activations