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. 9-RES-JB
    6. 21054
    Prev
    Next
    INDEX
    Explanations

    programming code snippets structured in a particular way

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming or command syntax in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     furthe
    -0.69
    Redd
    -0.66
    hedon
    -0.63
     Takeru
    -0.62
    heimer
    -0.62
     Rivers
    -0.61
     thereto
    -0.61
     Walton
    -0.60
     Hoo
    -0.59
     Gree
    -0.59
    POSITIVE LOGITS
    define
    1.10
    alias
    0.96
    export
    0.94
     import
    0.94
    import
    0.92
     ./
    0.91
     ns
    0.88
     âĶľâĶĢâĶĢ
    0.87
     declare
    0.86
    include
    0.86
    Activations Density 0.135%

    No Known Activations