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. 3546
    Prev
    Next
    INDEX
    Explanations

    instances of surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    the word "by" in various contexts, indicating reactions or evaluations

    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
    •layer 5 - surprise

    No Comments

    Negative Logits
    ayne
    -0.74
    Runner
    -0.74
    Reviewed
    -0.74
     ILCS
    -0.74
    aunder
    -0.73
    interrupted
    -0.68
    redits
    -0.68
     largeDownload
    -0.68
    heit
    -0.68
     teasp
    -0.68
    POSITIVE LOGITS
    products
    0.97
    product
    0.72
     Sapp
    0.71
     virtue
    0.70
     what
    0.68
    76561
    0.66
     seeing
    0.65
     Rampage
    0.65
     how
    0.64
     Heavenly
    0.62
    Activations Density 0.076%

    No Known Activations