© 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. 9-RES-JB
    11. 7371
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Jeffrey."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific person's name, indicating focus on that individual throughout the text

    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
    manship
    -0.90
    kers
    -0.84
    organic
    -0.80
    ker
    -0.80
    etimes
    -0.80
    align
    -0.79
    atom
    -0.79
    eries
    -0.79
    keye
    -0.77
    ider
    -0.76
    POSITIVE LOGITS
     Wilhelm
    0.83
     Douglas
    0.82
     Kessler
    0.81
     Anger
    0.79
     Stro
    0.77
     Kane
    0.77
     Angelo
    0.76
     Samuel
    0.75
     Cunningham
    0.75
     William
    0.75
    Activations Density 0.076%

    No Known Activations