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. 11-RES-JB
    6. 7424
    Prev
    Next
    INDEX
    Explanations

    starts of new sections or paragraphs in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Next" indicating a sequence or continuation in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lees
    -0.66
    kay
    -0.64
    zinski
    -0.62
    ocker
    -0.61
    ans
    -0.61
    arbon
    -0.61
    acons
    -0.59
    ondon
    -0.58
    ogether
    -0.57
    ITH
    -0.57
    POSITIVE LOGITS
     Steps
    1.10
    door
    1.04
     week
    0.98
     steps
    0.96
     month
    0.94
     Generation
    0.92
     generation
    0.87
     Month
    0.86
     door
    0.85
     year
    0.85
    Activations Density 0.028%

    No Known Activations