© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4238
    Prev
    Next
    INDEX
    Explanations

    phrases related to French language and culture

    oai_token-act-pair · gpt-3.5-turbo

    French words and phrases, especially those related to societal or cultural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arijuana
    -0.74
    District
    -0.72
     Kash
    -0.72
    USD
    -0.71
    Joshua
    -0.69
    Arizona
    -0.67
    defense
    -0.65
    Redd
    -0.65
    San
    -0.64
    Kansas
    -0.64
    POSITIVE LOGITS
     Ãł
    1.24
     qui
    1.19
     Ré
    1.19
     au
    1.16
     du
    1.13
     é
    1.12
     ré
    1.10
    ée
    1.10
     Ãī
    1.09
     dé
    1.09
    Activations Density 0.166%

    No Known Activations