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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 18477
    Prev
    Next
    INDEX
    Explanations

    lines related to computer programming, specifically those containing code syntax

    oai_token-act-pair · gpt-3.5-turbo

    code syntax and programming-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coffin
    -0.70
     camp
    -0.69
     slam
    -0.68
     raft
    -0.68
     escort
    -0.68
     mull
    -0.68
     interview
    -0.68
     wet
    -0.68
     stiff
    -0.68
     bunk
    -0.68
    POSITIVE LOGITS
    Notice
    1.66
    Alternatively
    1.56
    Which
    1.54
    Then
    1.48
    then
    1.44
    Note
    1.42
    Translation
    1.40
    Output
    1.38
    where
    1.38
    Example
    1.37
    Activations Density 0.149%

    No Known Activations