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. 8578
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words "write down" or "write off"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to documenting or writing actions

    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
    omaly
    -0.71
     predators
    -0.68
     sights
    -0.64
     choke
    -0.64
     distractions
    -0.62
    itimate
    -0.62
     tolerated
    -0.62
    htar
    -0.62
    chwitz
    -0.62
     accidental
    -0.61
    POSITIVE LOGITS
    DragonMagazine
    0.88
    ilk
    0.78
    advertisement
    0.77
    olkien
    0.74
    Journal
    0.74
    ibliography
    0.71
     Gazette
    0.69
    çļ
    0.68
    sheet
    0.68
     Aires
    0.68
    Activations Density 0.339%

    No Known Activations