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. 6-RES-JB
    6. 6256
    Prev
    Next
    INDEX
    Explanations

    fragments related to version control and software development processes, specifically focusing on commits, branches, patches, releases, and relevant code changes

    oai_token-act-pair · gpt-3.5-turbo

    references to code commits and version control concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otom
    -0.83
     telev
    -0.83
    acet
    -0.78
     Beir
    -0.76
    amina
    -0.75
     Ally
    -0.72
    apon
    -0.72
    ersive
    -0.72
     Toys
    -0.71
    phe
    -0.71
    POSITIVE LOGITS
     repository
    1.14
     repositories
    1.09
     upstream
    0.97
     Developers
    0.97
     repo
    0.96
     Documentation
    0.94
     Git
    0.91
     GitHub
    0.91
     linux
    0.91
     git
    0.91
    Activations Density 0.249%

    No Known Activations