© 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. 10-RES-JB
    11. 11017
    Prev
    Next
    INDEX
    Explanations

    information related to sports statistics and player performance

    oai_token-act-pair · gpt-3.5-turbo

    impressive athletic performance metrics and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.81
    ocrin
    -0.73
    soDeliveryDate
    -0.70
     Canaver
    -0.70
    insula
    -0.69
    argon
    -0.69
    actionDate
    -0.68
    abus
    -0.67
    MRI
    -0.65
    opian
    -0.64
    POSITIVE LOGITS
     scored
    1.34
     averaged
    1.26
     tallied
    1.22
     averaging
    1.21
     scoring
    1.14
     racked
    1.14
     tally
    1.10
     score
    1.07
     averages
    1.06
    scoring
    1.04
    Activations Density 0.323%

    No Known Activations