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. 11086
    Prev
    Next
    INDEX
    Explanations

    numerical expressions related to quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating minimum amounts or counts, particularly "at least" followed by numbers

    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
    NetMessage
    -0.79
    tions
    -0.77
    ãĥ¼ãĤ¯
    -0.77
    SourceFile
    -0.77
    taboola
    -0.77
    rift
    -0.69
    kai
    -0.69
    arily
    -0.69
    setup
    -0.67
    Reviewer
    -0.66
    POSITIVE LOGITS
     Beir
    0.74
     credible
    0.68
     Teresa
    0.66
     Innocent
    0.65
     129
    0.62
    een
    0.62
    foundland
    0.62
     six
    0.61
     eight
    0.61
    eight
    0.61
    Activations Density 0.021%

    No Known Activations