© 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. 2275
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and information, especially related to contracts, players' skills, and game performance

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

    terms related to sports players and their attributes

    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
     Journals
    -0.73
    asters
    -0.70
     Mothers
    -0.66
     Policies
    -0.63
     virginity
    -0.63
     miscar
    -0.61
     NAACP
    -0.61
     Wonderland
    -0.60
     slavery
    -0.60
    views
    -0.60
    POSITIVE LOGITS
     offensively
    1.36
     defensively
    1.31
     scorer
    1.22
     fielder
    1.18
     defender
    1.07
     athlet
    1.07
     hitter
    1.03
     passer
    1.03
     rusher
    1.02
     defenseman
    1.00
    Activations Density 0.212%

    No Known Activations