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. 8-RES-JB
    6. 14748
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences of special characters

    oai_token-act-pair · gpt-3.5-turbo

    specific introductory phrases or references that set the context for a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •contextual features
    fires on double newlines

    No Comments

    Negative Logits
     citiz
    -0.76
    hement
    -0.75
     neighb
    -0.75
     Schn
    -0.74
     submar
    -0.73
     shedding
    -0.71
     clin
    -0.70
     Murdoch
    -0.70
     commission
    -0.70
     Newsp
    -0.69
    POSITIVE LOGITS
    Reviewed
    1.14
    Description
    1.06
    CHAPTER
    1.06
    Page
    1.02
    ãĥ´ãĤ¡
    1.01
    LIN
    1.00
    Introduction
    0.97
    Instant
    0.96
    ccording
    0.96
    ItemImage
    0.96
    Activations Density 0.079%

    No Known Activations