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. 9-RES-JB
    6. 22492
    Prev
    Next
    INDEX
    Explanations

    high-ranking surnames or last names, particularly those containing variations of "Schr," "Sch," "Sh," "St," "Sc," and "S," and possibly including "ultz" and "midt."

    oai_token-act-pair · gpt-3.5-turbo

    names and variants of the surname "Schrute" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ont
    -0.74
    ELY
    -0.65
    cible
    -0.65
    e
    -0.63
    osterone
    -0.60
     Havana
    -0.60
    itous
    -0.59
     Chennai
    -0.59
    eas
    -0.59
     Rodham
    -0.58
    POSITIVE LOGITS
    enegger
    1.08
    geist
    1.05
    midt
    1.03
    bach
    0.97
    mann
    0.96
    meyer
    0.90
    bilt
    0.87
    ynski
    0.85
    auer
    0.78
    meier
    0.77
    Activations Density 0.146%

    No Known Activations