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. 9-RES-JB
    6. 404
    Prev
    Next
    INDEX
    Explanations

    lists or enumerations in a document

    oai_token-act-pair · gpt-3.5-turbo

    sentences introducing lists or summaries of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.79
    idable
    -0.68
    advertising
    -0.64
    ibles
    -0.62
     idols
    -0.61
    alties
    -0.60
     mattered
    -0.60
     disguise
    -0.60
     headaches
    -0.59
    assic
    -0.59
    POSITIVE LOGITS
     excerpt
    1.06
     excerpts
    1.04
     transcript
    0.86
     schematic
    0.84
     chronological
    0.83
     links
    0.83
     extracts
    0.81
    allery
    0.80
     screenshots
    0.80
    ographical
    0.79
    Activations Density 0.118%

    No Known Activations