© 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. 0-RES-JB
    11. 5362
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals receiving awards or recognition as the Player of the Year

    oai_token-act-pair · gpt-3.5-turbo

    references to various player awards in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weld
    -0.68
     haz
    -0.64
     congress
    -0.63
     pow
    -0.62
    oresc
    -0.62
     descent
    -0.62
    thens
    -0.62
     oxy
    -0.60
     politic
    -0.60
    UGE
    -0.60
    POSITIVE LOGITS
     Player
    3.84
    Player
    2.78
     Players
    2.46
     player
    2.35
    player
    2.29
    Players
    2.22
    players
    1.79
     players
    1.75
     Rookie
    1.60
     PLAY
    1.52
    Activations Density 0.016%

    No Known Activations