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. 16999
    Prev
    Next
    INDEX
    Explanations

    sports-related events and actions, such as field goals, free kicks, punts, and runs

    oai_token-act-pair · gpt-3.5-turbo

    elements related to scoring or attempts in competitive sports

    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
    rooms
    -0.75
    anamo
    -0.74
     organisations
    -0.73
    Scient
    -0.72
     Flavoring
    -0.70
     pronouns
    -0.69
    illac
    -0.69
     organising
    -0.68
     staffing
    -0.67
     Conserv
    -0.67
    POSITIVE LOGITS
     apiece
    0.96
     bounced
    0.94
     misses
    0.94
     attempt
    0.92
     scored
    0.92
     intercepted
    0.89
     midway
    0.88
     touchdown
    0.87
     sandwic
    0.86
     thrown
    0.84
    Activations Density 0.131%

    No Known Activations