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. 11767
    Prev
    Next
    INDEX
    Explanations

    instances where the word "one" is being emphasized

    oai_token-act-pair · gpt-3.5-turbo

    references to absence or lack of quantity

    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
    yrinth
    -0.68
    alth
    -0.66
    types
    -0.63
    bos
    -0.63
     notor
    -0.62
    atu
    -0.61
     sorts
    -0.60
    omsday
    -0.59
    comings
    -0.59
    loo
    -0.59
    POSITIVE LOGITS
     ounce
    1.20
     dime
    1.20
     penny
    0.98
     shred
    0.88
     nor
    0.88
     clue
    0.84
     inch
    0.82
     slightest
    0.80
     whatsoever
    0.78
     doubt
    0.78
    Activations Density 0.121%

    No Known Activations