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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 15102
    Prev
    Next
    INDEX
    Explanations

    keywords related to different numbered pages in a document or article

    oai_token-act-pair · gpt-3.5-turbo

    references to page numbers or document segmentation

    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
    ALLY
    -0.93
    CAST
    -0.92
    eware
    -0.80
    dayName
    -0.78
    eness
    -0.75
    rums
    -0.73
    iques
    -0.71
    eatures
    -0.69
    ivity
    -0.69
    oise
    -0.69
    POSITIVE LOGITS
    antry
    1.05
     Page
    0.84
    views
    0.78
    Page
    0.78
     McConnell
    0.73
    witz
    0.72
    ogue
    0.71
    Rank
    0.71
     Six
    0.68
     pancakes
    0.68
    Activations Density 0.013%

    No Known Activations