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. 8527
    Prev
    Next
    INDEX
    Explanations

    functions or method declarations in a programming context

    oai_token-act-pair · gpt-3.5-turbo

    programming function definitions and related keywords

    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
     Aram
    -0.75
    HAM
    -0.73
    dit
    -0.71
    aeus
    -0.71
    maid
    -0.71
    Nusra
    -0.67
    yss
    -0.67
    hai
    -0.67
     Saudis
    -0.67
    esley
    -0.66
    POSITIVE LOGITS
     func
    1.14
    func
    0.96
    iona
    0.82
     :=
    0.77
    bably
    0.74
    ctors
    0.71
    ð
    0.69
    unci
    0.68
    ĵĺ
    0.68
    outine
    0.66
    Activations Density 0.011%

    No Known Activations