© 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. 10-RES-JB
    11. 12912
    Prev
    Next
    INDEX
    Explanations

    French words or accents with characters like "é" and "ç"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the accented letter "é"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inson
    -0.68
     Hanson
    -0.67
     bulls
    -0.65
     sanctuary
    -0.62
     Asset
    -0.61
     Eck
    -0.59
     Sidd
    -0.59
     Amos
    -0.59
     Nelson
    -0.58
     Heidi
    -0.58
    POSITIVE LOGITS
    lé
    1.09
    ugi
    1.03
    clair
    1.03
    ré
    0.97
    sum
    0.96
    cé
    0.95
    conom
    0.94
    termin
    0.92
    phony
    0.91
    clamation
    0.91
    Activations Density 0.023%

    No Known Activations