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. 12761
    Prev
    Next
    INDEX
    Explanations

    words related to speaking engagements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Speaking" in various 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
    involved
    -0.78
    aden
    -0.72
    vier
    -0.67
    ught
    -0.67
    oute
    -0.66
    utz
    -0.64
    ste
    -0.63
    jl
    -0.62
    wart
    -0.62
    eer
    -0.62
    POSITIVE LOGITS
     apart
    0.78
     excerpts
    0.75
     anonymously
    0.75
     engagements
    0.75
     unden
    0.73
     fluent
    0.71
     aloud
    0.69
     candid
    0.69
     Speaking
    0.69
     frankly
    0.68
    Activations Density 0.024%

    No Known Activations