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. 1-RES-JB
    6. 18233
    Prev
    Next
    INDEX
    Explanations

    the word "Gill" followed by a number that is 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Gill"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     malfunction
    -0.68
     sight
    -0.67
    BOOK
    -0.64
    ension
    -0.63
     Extended
    -0.61
    ffer
    -0.59
     charge
    -0.59
     cytok
    -0.58
    xual
    -0.57
    anwhile
    -0.57
    POSITIVE LOGITS
    igan
    1.06
    iard
    1.02
    iland
    1.00
    iants
    0.96
    igans
    0.95
    aiman
    0.93
     Gill
    0.93
    wyn
    0.90
    espie
    0.89
    ieu
    0.85
    Activations Density 0.006%

    No Known Activations