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. 2330
    Prev
    Next
    INDEX
    Explanations

    code snippets involving periods

    oai_token-act-pair · gpt-3.5-turbo

    periods and sentence-ending punctuation

    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
     calves
    -0.86
     enthusi
    -0.84
     tyr
    -0.78
     undermin
    -0.78
     glim
    -0.78
     affili
    -0.78
     cod
    -0.78
     unheard
    -0.76
     perspect
    -0.75
     ivory
    -0.75
    POSITIVE LOGITS
    dll
    1.32
    exe
    1.24
    txt
    1.23
    prototype
    1.21
    html
    1.20
    xml
    1.17
    com
    1.14
    jpg
    1.12
    png
    1.11
    php
    1.08
    Activations Density 0.138%

    No Known Activations