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. 17757
    Prev
    Next
    INDEX
    Explanations

    links or references related to data formatting, particularly JSON and XML formats, along with error messages associated with formatting issues

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology related to data formatting and programming

    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
    ammy
    -0.86
    abouts
    -0.83
     Parkinson
    -0.80
     Malone
    -0.76
     Cunningham
    -0.74
     Lane
    -0.71
     dormant
    -0.71
     Burke
    -0.70
     Cao
    -0.70
    aido
    -0.69
    POSITIVE LOGITS
     json
    1.43
     formatted
    1.43
     JSON
    1.41
     UTF
    1.40
     format
    1.38
     parsed
    1.35
     encoding
    1.34
    utf
    1.31
    UTF
    1.31
     formatting
    1.31
    Activations Density 0.194%

    No Known Activations