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. 3-RES-JB
    6. 938
    Prev
    Next
    INDEX
    Explanations

    words related to a wide or extensive scope or range

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "broad" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.90
    LV
    -0.84
     Disciple
    -0.77
    aminer
    -0.72
    ICAN
    -0.70
     Keeper
    -0.69
    Dialogue
    -0.68
     Million
    -0.68
     Train
    -0.66
     Frankenstein
    -0.66
    POSITIVE LOGITS
    sheet
    1.39
    sheets
    1.27
    leaf
    1.09
     spectrum
    1.00
     strokes
    0.99
    ening
    0.99
    sword
    0.98
     daylight
    0.95
    itzer
    0.84
     swath
    0.84
    Activations Density 0.013%

    No Known Activations