© 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. 24447
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of significant events or actions in a game or competition

    oai_token-act-pair · gpt-3.5-turbo

    references to specific games or match details

    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
    anian
    -0.76
    phia
    -0.71
     Purg
    -0.69
    istani
    -0.67
    ROR
    -0.65
     Mehran
    -0.64
    LECT
    -0.63
    abel
    -0.63
    geries
    -0.63
    elist
    -0.61
    POSITIVE LOGITS
    plan
    1.09
    winning
    1.04
    winner
    0.92
     MVP
    0.85
     winner
    0.83
    planned
    0.82
     chang
    0.81
    breaker
    0.79
    win
    0.78
     breaker
    0.76
    Activations Density 0.075%

    No Known Activations