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. 4-RES-JB
    6. 12673
    Prev
    Next
    INDEX
    Explanations

    the name "Gill" specifically followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Gill" and its variations

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

    No Comments

    Negative Logits
    BOOK
    -0.65
    ension
    -0.63
     sight
    -0.62
    xual
    -0.62
     compr
    -0.61
    ×IJ
    -0.60
    VALUE
    -0.60
     malfunction
    -0.59
    ffer
    -0.58
     beg
    -0.58
    POSITIVE LOGITS
    igan
    1.17
    iard
    1.06
    iants
    1.05
    iland
    1.04
    igans
    0.97
    espie
    0.97
    wyn
    0.94
    iband
    0.93
    ibr
    0.85
    iage
    0.85
    Activations Density 0.011%

    No Known Activations