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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9787
    Prev
    Next
    INDEX
    Explanations

    references to decisions made by officials in a sports context, especially related to penalties and disciplinary actions

    oai_token-act-pair · gpt-3.5-turbo

    references to disciplinary actions in 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
    igslist
    -0.96
    achine
    -0.86
    rowth
    -0.85
    Zip
    -0.84
    growth
    -0.80
     Surviv
    -0.79
    Transform
    -0.77
    ARCH
    -0.77
    Ń·
    -0.76
    yll
    -0.73
    POSITIVE LOGITS
     referee
    1.86
     referees
    1.82
     Fifa
    1.57
     UEFA
    1.49
     Penalty
    1.49
     penalty
    1.41
     offic
    1.35
     penalties
    1.35
     foul
    1.32
     FIFA
    1.32
    Activations Density 0.785%

    No Known Activations