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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 5-RES-JB
    6. 11225
    Prev
    Next
    INDEX
    Explanations

    mentions of sports team rosters

    oai_token-act-pair · gpt-3.5-turbo

    references to sports team rosters

    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
    cart
    -0.77
    ryn
    -0.73
     Ang
    -0.71
     Gaul
    -0.68
    rir
    -0.64
    bows
    -0.63
     Belt
    -0.63
     Greenwich
    -0.63
     Riv
    -0.62
     vaginal
    -0.62
    POSITIVE LOGITS
     roster
    0.99
     rosters
    0.99
     backups
    0.84
     lineup
    0.77
     mates
    0.77
    Players
    0.77
     turnover
    0.75
    mates
    0.73
    icter
    0.73
    DAQ
    0.73
    Activations Density 0.021%

    No Known Activations