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. 3120
    Prev
    Next
    INDEX
    Explanations

    the name "Carol" or "Daryl" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Carol" 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
    Reply
    -0.73
    asonable
    -0.71
    claimer
    -0.71
    fix
    -0.68
    utils
    -0.68
    facts
    -0.68
    hower
    -0.67
    election
    -0.67
    flat
    -0.67
    change
    -0.67
    POSITIVE LOGITS
     Burnett
    1.02
    otte
    0.95
    inas
    0.88
     Carol
    0.81
     Sue
    0.79
     McDonnell
    0.77
    ucci
    0.76
    lee
    0.74
    olina
    0.74
     Rae
    0.73
    Activations Density 0.014%

    No Known Activations