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. 6827
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Lucy" in discussions about various topics and scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Lucy

    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
    alez
    -0.99
    raints
    -0.86
    ifact
    -0.77
    */(
    -0.77
    lopp
    -0.73
    =]
    -0.71
    oln
    -0.71
    д
    -0.70
    itect
    -0.70
    ebin
    -0.70
    POSITIVE LOGITS
     Lucy
    0.89
     Liu
    0.89
    cles
    0.87
    cy
    0.78
     Hale
    0.75
     Yao
    0.74
    lihood
    0.73
    Lu
    0.72
    itably
    0.70
    itable
    0.69
    Activations Density 0.007%

    No Known Activations