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. 8-RES-JB
    6. 15798
    Prev
    Next
    INDEX
    Explanations

    positive comments or praise related to sports coaches and their decisions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of coaches and their decisions or performances in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ospons
    -0.78
    Fax
    -0.74
     Satanic
    -0.73
     uter
    -0.70
    Eva
    -0.69
     Membership
    -0.68
    â̦â̦â̦â̦â̦â̦â̦â̦
    -0.67
     ACLU
    -0.67
     Parenthood
    -0.67
    selves
    -0.66
    POSITIVE LOGITS
     coaching
    0.98
     coached
    0.91
     sacked
    0.91
    ynasty
    0.83
     Teams
    0.82
    players
    0.80
     appointing
    0.80
    Players
    0.78
     rookies
    0.78
     coaches
    0.78
    Activations Density 0.457%

    No Known Activations