© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 23194
    Prev
    Next
    INDEX
    Explanations

    the name "Kelly" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kelly"

    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
    xual
    -0.75
     Flavoring
    -0.73
    ensical
    -0.73
    omething
    -0.71
     glim
    -0.71
     disadvant
    -0.70
    nces
    -0.68
    eers
    -0.68
    sent
    -0.67
    raints
    -0.65
    POSITIVE LOGITS
     Slater
    0.93
     Kelly
    0.82
    Anne
    0.79
     Clarkson
    0.79
    town
    0.77
    sey
    0.75
     Sue
    0.75
    eland
    0.73
    lee
    0.73
     Fitzpatrick
    0.72
    Activations Density 0.006%

    No Known Activations