Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 19138
    Prev
    Next
    INDEX
    Explanations

    sports scores or results in the format of team A score, team B score

    oai_token-act-pair · gpt-3.5-turbo

    score statistics from sports games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     evenings
    -0.67
     Clarks
    -0.63
     BM
    -0.63
     Burma
    -0.62
     workshops
    -0.61
     mirrors
    -0.61
     Myanmar
    -0.60
     kitchens
    -0.60
     Mara
    -0.60
     clusters
    -0.59
    POSITIVE LOGITS
    year
    1.26
    game
    1.20
    minute
    1.18
    point
    1.13
    straight
    1.12
    gamer
    1.09
    seed
    1.06
    goal
    1.06
    season
    1.05
    match
    1.05
    Activations Density 0.052%

    No Known Activations