© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4878
    Prev
    Next
    INDEX
    Explanations

    information related to sports tournaments and rules, specifically focusing on team positions, divisions, and qualifiers

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    information related to tournament structures and schedules in competitive events

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     cellul
    -0.77
     sensing
    -0.69
     fragrance
    -0.69
     bicy
    -0.69
    dylib
    -0.68
     recept
    -0.68
     photoc
    -0.68
    ascript
    -0.67
     recycling
    -0.67
     porous
    -0.67
    POSITIVE LOGITS
     Tournament
    1.45
     MLG
    1.42
     tournament
    1.39
     Starcraft
    1.37
     StarCraft
    1.37
    Players
    1.37
     tournaments
    1.34
    ournament
    1.34
     GSL
    1.33
     eSports
    1.32
    Activations Density 0.489%

    No Known Activations