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. 12365
    Prev
    Next
    INDEX
    Explanations

    words related to legal professionals, specifically focusing on the surname "Edwards."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Edwards."

    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
    efully
    -0.86
    ographed
    -0.75
    eful
    -0.70
    thing
    -0.69
    ctica
    -0.67
    akia
    -0.66
    BOOK
    -0.66
    apest
    -0.66
    typ
    -0.66
    ãĥĩãĤ£
    -0.64
    POSITIVE LOGITS
    burgh
    0.91
    pires
    0.90
    monton
    0.80
    monds
    0.77
    shire
    0.77
    ville
    0.76
    bury
    0.75
    inburgh
    0.75
    mond
    0.74
    eton
    0.72
    Activations Density 0.011%

    No Known Activations