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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 9163
    Prev
    Next
    INDEX
    Explanations

    names of sports players and statistical information related to sports

    oai_token-act-pair · gpt-3.5-turbo

    sports-related data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Feminist
    -0.93
     ®
    -0.86
     UNESCO
    -0.83
    enegger
    -0.75
     Capitalism
    -0.75
     Quartz
    -0.71
     Prohibition
    -0.70
     condoms
    -0.70
    pour
    -0.69
     diplom
    -0.68
    POSITIVE LOGITS
     teammate
    1.12
     rookie
    1.12
    Coach
    1.07
     coach
    1.05
     rookies
    1.00
     Rookie
    0.99
     teammates
    0.97
     scouting
    0.95
     coaches
    0.95
     league
    0.94
    Activations Density 0.283%

    No Known Activations