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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3266
    Prev
    Next
    INDEX
    Explanations

    references related to French culture or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the French

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.89
    iary
    -0.88
    okemon
    -0.86
    oots
    -0.83
    )=(
    -0.83
    iations
    -0.80
    ivals
    -0.79
    ividual
    -0.78
    yrs
    -0.78
    oldemort
    -0.75
    POSITIVE LOGITS
     fries
    0.97
     Alps
    0.86
     citiz
    0.85
     French
    0.82
     Marse
    0.78
     countryside
    0.78
     antioxid
    0.76
     Connection
    0.75
     France
    0.75
     Riv
    0.74
    Activations Density 0.008%

    No Known Activations