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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16593
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, particularly "Patterson" and "Pearson."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names of people, likely the name "Patterson"

    oai_token-act-pair · gpt-3.5-turbo
    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
    76561
    -0.97
    pipe
    -0.78
    ãĥ´
    -0.77
    ERO
    -0.67
    BuyableInstoreAndOnline
    -0.66
    cal
    -0.65
    semble
    -0.65
    AMES
    -0.64
    ppo
    -0.64
    ¥
    -0.64
    POSITIVE LOGITS
     Patterson
    1.12
     Square
    0.75
    terson
    0.73
    endish
    0.71
    witz
    0.70
    olini
    0.69
    riott
    0.67
    rail
    0.67
    urdy
    0.67
     McConnell
    0.66
    Activations Density 0.008%

    No Known Activations