© 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. 11-RES-JB
    11. 22677
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performance, particularly points and rebounds

    oai_token-act-pair · gpt-3.5-turbo

    statistical metrics related to basketball performance, specifically points, rebounds, and assists

    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
     Canaver
    -0.74
    76561
    -0.71
    Operation
    -0.63
    udeb
    -0.61
    beard
    -0.61
    llah
    -0.59
    atom
    -0.59
    Fact
    -0.58
    ctors
    -0.57
     Habit
    -0.57
    POSITIVE LOGITS
     (.
    0.80
     per
    0.78
     apiece
    0.76
     guard
    0.75
     scored
    0.74
    illard
    0.73
     rebounds
    0.73
    reau
    0.70
     guards
    0.66
     vs
    0.66
    Activations Density 0.030%

    No Known Activations