© 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. 9-RES-JB
    11. 5895
    Prev
    Next
    INDEX
    Explanations

    keywords related to sports and education, particularly focusing on college athletics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to college sports and player development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solitaire
    -0.70
    fm
    -0.69
     Sparrow
    -0.69
     Gingrich
    -0.68
     ®
    -0.68
    attr
    -0.67
    aph
    -0.67
    aurus
    -0.67
    orah
    -0.66
     Harmony
    -0.65
    POSITIVE LOGITS
     scouting
    1.16
     signings
    1.11
     leagues
    1.07
     league
    1.06
     scouts
    1.05
     talent
    1.03
    football
    1.02
    Football
    1.02
     football
    1.01
     coaching
    1.00
    Activations Density 0.158%

    No Known Activations