© 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. 21989
    Prev
    Next
    INDEX
    Explanations

    events that end in a draw or tie

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the outcome of competitions or matches

    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
    ersive
    -0.76
    catentry
    -0.74
    ngth
    -0.72
    spect
    -0.69
    soType
    -0.68
    compan
    -0.68
     largeDownload
    -0.65
    vern
    -0.64
    Express
    -0.64
    Introduced
    -0.63
    POSITIVE LOGITS
     defeat
    1.41
     forfeit
    1.40
     victory
    1.37
     defeats
    1.31
     win
    1.30
     Loss
    1.28
     wins
    1.28
    Winner
    1.26
     loser
    1.26
     winner
    1.24
    Activations Density 0.457%

    No Known Activations