© 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. 2037
    Prev
    Next
    INDEX
    Explanations

    sports statistics, specifically points and rebounds scored by players

    oai_token-act-pair · gpt-3.5-turbo

    sports statistics and performance metrics

    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
    Filename
    -0.69
    Picture
    -0.66
    once
    -0.66
    quit
    -0.66
    dit
    -0.65
     fres
    -0.64
    alone
    -0.63
    imester
    -0.62
     Canaver
    -0.62
     Suff
    -0.61
    POSITIVE LOGITS
     rebounds
    1.40
     assists
    1.04
     steals
    1.02
     boards
    0.83
     turnovers
    0.82
     touchdowns
    0.79
     interceptions
    0.79
     steal
    0.74
    pt
    0.72
     rushes
    0.71
    Activations Density 0.065%

    No Known Activations