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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 11149
    Prev
    Next
    INDEX
    Explanations

    references to French-related entities or topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "French."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abilia
    -0.71
    NetMessage
    -0.66
     conclud
    -0.65
     contend
    -0.65
    Path
    -0.64
    Bitcoin
    -0.64
    olith
    -0.64
    utra
    -0.63
    seek
    -0.62
    Protect
    -0.62
    POSITIVE LOGITS
     French
    3.53
    French
    3.14
     french
    2.60
     Frenchman
    2.42
     France
    2.31
     Belgian
    2.28
    France
    2.25
     Dutch
    2.20
     Spanish
    2.12
     Italian
    2.08
    Activations Density 0.029%

    No Known Activations