© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 18918
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Nancy."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Nancy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gall
    -0.75
    omet
    -0.68
     kil
    -0.68
    kil
    -0.66
    aer
    -0.66
    GG
    -0.64
    ta
    -0.64
     arbitration
    -0.64
     pupil
    -0.63
    brew
    -0.62
    POSITIVE LOGITS
     Nancy
    3.64
     Pelosi
    1.64
     Erica
    1.50
     Donna
    1.49
     Betsy
    1.41
     Linda
    1.41
     Anita
    1.37
     Eleanor
    1.37
     Dianne
    1.37
     Samantha
    1.36
    Activations Density 0.015%

    No Known Activations