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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 5845
    Prev
    Next
    INDEX
    Explanations

    French words or names

    oai_token-act-pair · gpt-3.5-turbo

    words related to accents and pronunciations in different languages

    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
    yip
    -0.74
    perm
    -0.69
    seek
    -0.69
     calculator
    -0.67
    ldon
    -0.66
    vae
    -0.66
    drm
    -0.66
     gears
    -0.65
    ittle
    -0.64
     hover
    -0.64
    POSITIVE LOGITS
     Ré
    1.03
     Mé
    1.02
    Marie
    0.96
     Franç
    0.96
    è
    0.96
    rique
    0.91
     François
    0.90
    ée
    0.87
     Ãł
    0.87
     Ãī
    0.87
    Activations Density 0.192%

    No Known Activations