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. 11710
    Prev
    Next
    INDEX
    Explanations

    quotations and dialogues with periods at the end

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and quotation marks

    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
     separated
    -0.73
     allied
    -0.70
     prelim
    -0.69
     heck
    -0.67
     furnace
    -0.67
     imperson
    -0.65
     executed
    -0.64
     spir
    -0.63
     sucker
    -0.63
     doomed
    -0.63
    POSITIVE LOGITS
     âĢķ
    1.04
    BuyableInstoreAndOnline
    0.98
    >>\
    0.97
    Hey
    0.95
    Yeah
    0.95
     ["
    0.90
    Alright
    0.90
    Wow
    0.89
    Okay
    0.88
    Hello
    0.85
    Activations Density 0.057%

    No Known Activations