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. 0-RES-JB
    6. 9212
    Prev
    Next
    INDEX
    Explanations

    mention of trademarks or actions related to trademarks

    oai_token-act-pair · gpt-3.5-turbo

    references to trademarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cells
    -0.78
    grades
    -0.76
    qs
    -0.73
    seq
    -0.69
    esley
    -0.67
    als
    -0.66
    iles
    -0.64
     Chap
    -0.62
    iew
    -0.62
    alloc
    -0.62
    POSITIVE LOGITS
     trademark
    4.17
     trademarks
    2.99
     patented
    1.84
     patent
    1.71
     Patent
    1.45
     patents
    1.43
     Trad
    1.35
     copyright
    1.30
     logo
    1.26
     tradem
    1.22
    Activations Density 0.023%

    No Known Activations