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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3263
    Prev
    Next
    INDEX
    Explanations

    references to sports teams

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orage
    -0.75
    asy
    -0.71
    heit
    -0.70
     Gutenberg
    -0.70
    apest
    -0.69
    owan
    -0.68
     Vanity
    -0.65
    cape
    -0.64
    agogue
    -0.63
     Supplement
    -0.63
    POSITIVE LOGITS
     teams
    3.67
     Teams
    3.00
     squads
    2.36
     team
    2.26
    team
    2.09
    Team
    2.00
     rosters
    1.92
     TEAM
    1.91
     Team
    1.85
     teammates
    1.76
    Activations Density 0.024%

    No Known Activations