© 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. 2482
    Prev
    Next
    INDEX
    Explanations

    sport-related terms or descriptions

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

    phrases indicating potential or performance upgrade in players

    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
    idents
    -0.82
    terness
    -0.79
    onduct
    -0.78
    actionDate
    -0.75
    earances
    -0.72
    bara
    -0.72
    attacks
    -0.72
    rollers
    -0.72
    rers
    -0.70
    parents
    -0.70
    POSITIVE LOGITS
     bargain
    1.04
     lockdown
    0.99
     lock
    0.98
     steal
    0.97
     starter
    0.92
     Heisman
    0.91
     handc
    0.89
     sleeper
    0.88
     lottery
    0.88
     downgrade
    0.88
    Activations Density 0.121%

    No Known Activations