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. 7-RES-JB
    6. 21973
    Prev
    Next
    INDEX
    Explanations

    functions and keywords related to programming languages, such as "GetString()" and "#define"

    oai_token-act-pair · gpt-3.5-turbo

    programming functions and code-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TBA
    -0.81
     Staples
    -0.65
     NTS
    -0.64
    ][/
    -0.64
     Hayden
    -0.64
     sweat
    -0.62
     Fifth
    -0.61
     Univ
    -0.61
     Chu
    -0.60
     Watts
    -0.59
    POSITIVE LOGITS
    ().
    1.15
    ()
    1.02
    foo
    1.01
    (),
    1.01
    dir
    0.95
    Debug
    0.92
    example
    0.91
    Async
    0.88
     foo
    0.88
    NULL
    0.86
    Activations Density 0.241%

    No Known Activations