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. 0-RES-JB
    6. 16021
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions related to coding or programming

    oai_token-act-pair · gpt-3.5-turbo

    references to coding and programming activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mour
    -0.88
     Prosper
    -0.82
     Sovereign
    -0.78
    undy
    -0.74
     Pet
    -0.73
    umph
    -0.72
     Peterson
    -0.72
    Pet
    -0.71
    â̦â̦â̦â̦â̦â̦â̦â̦
    -0.69
    erenn
    -0.69
    POSITIVE LOGITS
     coding
    3.78
     coded
    2.16
     encoding
    2.04
    coded
    1.70
     programming
    1.69
     codes
    1.69
     programmers
    1.57
    codes
    1.56
     code
    1.54
     encode
    1.46
    Activations Density 0.009%

    No Known Activations