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. 11-RES-JB
    6. 19823
    Prev
    Next
    INDEX
    Explanations

    references to various coaches across different sports

    oai_token-act-pair · gpt-3.5-turbo

    references to sports coaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yuan
    -0.66
     flaw
    -0.65
     corridor
    -0.64
    selves
    -0.64
    conn
    -0.63
     allowances
    -0.62
     poss
    -0.62
     recipients
    -0.61
    theless
    -0.61
    awatts
    -0.61
    POSITIVE LOGITS
     Bruce
    0.91
     Randy
    0.91
     Gregg
    0.90
     Mike
    0.86
     Dana
    0.85
     Steve
    0.85
     Todd
    0.84
     Dave
    0.84
     Pete
    0.83
     Luke
    0.82
    Activations Density 0.042%

    No Known Activations