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. 6660
    Prev
    Next
    INDEX
    Explanations

    names related to a common surname "Gall" with a numerical score following it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Gall" as a significant subject within the text

    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
    BOOK
    -0.79
    terday
    -0.70
    ccording
    -0.67
    CLASSIFIED
    -0.65
     huh
    -0.64
     Reloaded
    -0.63
     EDITION
    -0.63
     dear
    -0.61
     reality
    -0.60
    displayText
    -0.60
    POSITIVE LOGITS
    eries
    1.09
    oway
    1.03
    antry
    1.03
    agher
    1.00
    ogly
    0.99
     Gall
    0.97
    atin
    0.94
    oqu
    0.91
    ium
    0.91
    Gall
    0.91
    Activations Density 0.007%

    No Known Activations