© 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. 4-RES-JB
    11. 3619
    Prev
    Next
    INDEX
    Explanations

    French accents such as 'dé' and 'ré'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of diacritical marks in words

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

    No Comments

    Negative Logits
    inson
    -0.74
    atform
    -0.73
    omaly
    -0.73
    ollah
    -0.72
    astic
    -0.72
    ierrez
    -0.71
    ible
    -0.70
    ageddon
    -0.69
    iful
    -0.69
    iazep
    -0.68
    POSITIVE LOGITS
     é
    0.89
     Dame
    0.89
    ité
    0.87
    ré
    0.85
     dé
    0.85
     ré
    0.84
     jour
    0.78
    cé
    0.77
    dain
    0.75
    vre
    0.75
    Activations Density 0.012%

    No Known Activations