Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 352
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a full stop

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, specifically periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     volunte
    -0.75
     holdings
    -0.71
     contam
    -0.71
     pocket
    -0.70
     undet
    -0.68
     manual
    -0.67
     docking
    -0.67
     dispers
    -0.66
     bidder
    -0.65
     harvest
    -0.65
    POSITIVE LOGITS
     Thankfully
    1.47
     Granted
    1.39
     Sure
    1.34
     Fortunately
    1.34
     Luckily
    1.34
     Whether
    1.33
     Certainly
    1.33
     Sadly
    1.29
     Especially
    1.28
     Surely
    1.25
    Activations Density 0.367%

    No Known Activations