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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16966
    Prev
    Next
    INDEX
    Explanations

    syntax patterns commonly found in code scripts

    oai_token-act-pair · gpt-3.5-turbo

    programming and syntax-related conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corrid
    -0.69
     intangible
    -0.65
     Wonderland
    -0.65
     Volvo
    -0.65
     glim
    -0.63
     Ys
    -0.62
     Wag
    -0.61
    ĸļ
    -0.60
     brains
    -0.58
     citiz
    -0.58
    POSITIVE LOGITS
    needed
    0.76
    null
    0.73
    ==
    0.72
     !
    0.72
    msg
    0.71
    Dispatch
    0.70
     DEBUG
    0.70
    defined
    0.70
     &&
    0.69
     <=
    0.68
    Activations Density 0.039%

    No Known Activations