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. 10-RES-JB
    6. 9701
    Prev
    Next
    INDEX
    Explanations

    instances of multiple occurrences or repetitions

    oai_token-act-pair · gpt-3.5-turbo

    references to repeated actions or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rats
    -0.71
    aceous
    -0.69
    rera
    -0.68
     heirs
    -0.64
    liction
    -0.64
    urated
    -0.63
    umbn
    -0.63
     Redemption
    -0.63
    ourt
    -0.63
    eton
    -0.62
    POSITIVE LOGITS
     consecut
    0.96
     throughout
    0.94
     apiece
    0.89
     during
    0.86
     before
    0.86
    points
    0.78
    cale
    0.75
     since
    0.71
     beforehand
    0.70
     ago
    0.68
    Activations Density 0.060%

    No Known Activations