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. 3-RES-JB
    6. 6828
    Prev
    Next
    INDEX
    Explanations

    text related to coding and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    references to programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iatus
    -0.98
    iversal
    -0.90
     Flavoring
    -0.88
    abouts
    -0.76
    swer
    -0.74
    SPONSORED
    -0.73
    strous
    -0.71
    cffff
    -0.71
    Ń·
    -0.70
     Wynne
    -0.70
    POSITIVE LOGITS
     snippet
    1.28
     code
    1.13
    code
    1.00
    base
    0.99
     snippets
    0.97
     codes
    0.91
     fragment
    0.89
     snipp
    0.86
     repository
    0.83
    codes
    0.82
    Activations Density 0.014%

    No Known Activations