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. 11-RES-JB
    6. 19594
    Prev
    Next
    INDEX
    Explanations

    programming commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of opening parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buoy
    -0.71
     Arn
    -0.70
     Mour
    -0.69
     Tall
    -0.69
     perme
    -0.69
     resur
    -0.68
     Reich
    -0.68
     fraternity
    -0.66
     Samar
    -0.66
     contempor
    -0.66
    POSITIVE LOGITS
    optional
    1.74
    unless
    1.67
    requires
    1.64
    usually
    1.64
    assuming
    1.62
    depending
    1.62
    same
    1.57
    similar
    1.57
    recomm
    1.54
    see
    1.54
    Activations Density 0.120%

    No Known Activations