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. 1-RES-JB
    6. 17508
    Prev
    Next
    INDEX
    Explanations

    terms related to programming syntax

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "syntax" and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kore
    -0.87
    ECD
    -0.81
     Gund
    -0.80
     Gamble
    -0.75
     Gunn
    -0.74
    birth
    -0.69
     Hanson
    -0.69
     Ern
    -0.67
     Sherman
    -0.66
    yer
    -0.65
    POSITIVE LOGITS
     syntax
    1.39
    ntax
    1.23
     notation
    0.98
    thia
    0.85
     spelling
    0.84
     markup
    0.84
     parser
    0.84
    avascript
    0.83
     language
    0.82
     parsing
    0.82
    Activations Density 0.011%

    No Known Activations