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. 17897
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to "First Lady" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to First Ladies and their roles

    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
    sett
    -0.82
    aic
    -0.76
    elsen
    -0.75
    Sensor
    -0.73
    CAST
    -0.67
    obyl
    -0.65
    adr
    -0.64
    rawdownloadcloneembedreportprint
    -0.64
    estic
    -0.63
    apor
    -0.61
    POSITIVE LOGITS
     Melania
    0.92
    thood
    0.69
     Grace
    0.68
     Governors
    0.68
     Jacqu
    0.68
     Martha
    0.67
    apolog
    0.64
    cellence
    0.64
     Jindal
    0.63
     pard
    0.63
    Activations Density 0.035%

    No Known Activations