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. 16834
    Prev
    Next
    INDEX
    Explanations

    instances of numbers followed by punctuation

    oai_token-act-pair · gpt-3.5-turbo

    numbers and numerical expressions in the text

    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
     elevation
    -0.74
     padd
    -0.73
     swallowing
    -0.71
     guarding
    -0.71
     travers
    -0.70
     pastoral
    -0.68
     brid
    -0.68
     brav
    -0.67
    hung
    -0.67
     whipping
    -0.65
    POSITIVE LOGITS
     SHARES
    1.01
     NCT
    0.86
    maxwell
    0.80
    ertodd
    0.80
     ·
    0.76
    rd
    0.75
    nd
    0.75
     Facts
    0.74
     Expand
    0.73
    :{
    0.73
    Activations Density 0.099%

    No Known Activations