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. 3-RES-JB
    6. 21810
    Prev
    Next
    INDEX
    Explanations

    words related to cocoa and related products

    oai_token-act-pair · gpt-3.5-turbo

    references to cocoa and related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naires
    -0.79
     Frankenstein
    -0.68
     Duchess
    -0.68
     Generations
    -0.64
     IST
    -0.63
    uyomi
    -0.63
     Ghostbusters
    -0.62
    VERTIS
    -0.62
     Pathfinder
    -0.61
    shire
    -0.61
    POSITIVE LOGITS
    keye
    1.01
     coc
    0.99
    keyes
    0.98
    urrency
    0.87
    aleb
    0.85
    wana
    0.85
    aine
    0.84
    leans
    0.82
    oby
    0.81
    ilage
    0.81
    Activations Density 0.010%

    No Known Activations