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. 11032
    Prev
    Next
    INDEX
    Explanations

    resolutions related to screen display, particularly focusing on the specific resolution numbers being mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years, particularly in the 1900s

    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
    resso
    -0.96
    lace
    -0.73
    holder
    -0.72
    leton
    -0.71
    ensor
    -0.70
    site
    -0.70
    Guard
    -0.69
    avis
    -0.69
    intosh
    -0.68
    atl
    -0.68
    POSITIVE LOGITS
    576
    0.77
    1920
    0.77
     ILCS
    0.72
    elsius
    0.71
    âĢķ
    0.71
    terness
    0.70
    iculture
    0.69
    ãĥĥãĥĪ
    0.69
    900
    0.66
     Osw
    0.66
    Activations Density 0.009%

    No Known Activations