© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21000
    Prev
    Next
    INDEX
    Explanations

    sport-related terms or information

    oai_token-act-pair · gpt-3.5-turbo

    significant information related to sports teams and their schedules

    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
    reprene
    -0.84
     Anon
    -0.76
     Voc
    -0.73
    verified
    -0.72
    UTH
    -0.72
     Cosponsors
    -0.72
    artisan
    -0.71
     Quote
    -0.71
    ickr
    -0.70
    ploma
    -0.70
    POSITIVE LOGITS
     matchups
    1.68
     playoff
    1.66
     playoffs
    1.66
     postseason
    1.56
     Playoff
    1.44
     Playoffs
    1.42
     matchup
    1.40
     games
    1.38
     bye
    1.27
     contests
    1.23
    Activations Density 0.487%

    No Known Activations