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. 8-RES-JB
    6. 8868
    Prev
    Next
    INDEX
    Explanations

    examples of phrases that provide additional information or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" as a signal of contrast or exception in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Merit
    -0.68
    illed
    -0.62
    stre
    -0.62
    tnc
    -0.60
    guard
    -0.59
    AFTA
    -0.59
    andowski
    -0.58
    usting
    -0.58
    acho
    -0.57
    edu
    -0.57
    POSITIVE LOGITS
    tons
    1.17
     beware
    1.04
    chery
    0.93
    yip
    0.93
     fortunately
    0.92
     excludes
    0.92
     preferably
    0.92
     luckily
    0.91
     alas
    0.89
     interestingly
    0.85
    Activations Density 0.195%

    No Known Activations