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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4409
    Prev
    Next
    INDEX
    Explanations

    French accented characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "é" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utterstock
    -0.80
    pread
    -0.75
    INESS
    -0.73
    enged
    -0.70
    etsk
    -0.68
     Cobra
    -0.68
    ageddon
    -0.67
    Spread
    -0.65
     redistributed
    -0.64
     Blazers
    -0.64
    POSITIVE LOGITS
    lé
    1.19
    rez
    0.92
    vez
    0.92
     Dame
    0.91
     é
    0.87
    ré
    0.83
    ité
    0.82
    ration
    0.82
    cé
    0.82
    é
    0.81
    Activations Density 0.013%

    No Known Activations