© 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. 6928
    Prev
    Next
    INDEX
    Explanations

    terms related to baseball and the different levels of the sport (e.g., Triple-A, Double-A)

    oai_token-act-pair · gpt-3.5-turbo

    references to Triple-A baseball, including player performance and statistics

    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
    igmat
    -0.83
    Downloadha
    -0.76
    ITNESS
    -0.67
    manship
    -0.64
    erv
    -0.62
    endez
    -0.62
    hof
    -0.61
    heit
    -0.60
    papers
    -0.60
    olson
    -0.59
    POSITIVE LOGITS
    header
    1.04
    plets
    0.95
     digits
    0.95
    headers
    0.93
    plet
    0.91
     Crown
    0.82
    ts
    0.75
     digit
    0.74
     elig
    0.73
     Trouble
    0.71
    Activations Density 0.031%

    No Known Activations