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. 14349
    Prev
    Next
    INDEX
    Explanations

    strings of characters representing variables in a programming context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "String" and its variants in programming contexts

    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
    undai
    -0.86
    artifacts
    -0.81
     livest
    -0.80
    tical
    -0.80
    hyde
    -0.78
    yrinth
    -0.76
    omorphic
    -0.75
    esty
    -0.74
    hap
    -0.74
    cence
    -0.74
    POSITIVE LOGITS
    Builder
    0.96
    ified
    0.82
    Array
    0.78
    String
    0.73
    Buffer
    0.72
     bikini
    0.70
    ification
    0.70
     literal
    0.69
    ify
    0.69
     String
    0.68
    Activations Density 0.008%

    No Known Activations