Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11069
    Prev
    Next
    INDEX
    Explanations

    terms related to const- as a prefix in programming

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "const" and its variations, indicating a focus on programming or technical contexts

    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
    kefeller
    -0.80
     Kamp
    -0.76
    ebook
    -0.74
    baum
    -0.73
     TAMADRA
    -0.72
     Mellon
    -0.71
    lez
    -0.71
    chwitz
    -0.70
    eday
    -0.70
     Reborn
    -0.70
    POSITIVE LOGITS
     const
    3.87
    const
    2.11
     Const
    1.78
     Constable
    1.69
    Const
    1.66
     constants
    1.12
     constellation
    1.09
     pert
    1.02
     uint
    1.00
    uint
    0.99
    Activations Density 0.014%

    No Known Activations