© 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. 6-RES-JB
    11. 9297
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Mitch"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mitch McConnell."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -1.09
    ciating
    -0.71
    ettel
    -0.70
    dylib
    -0.69
    ISM
    -0.68
    hibited
    -0.67
    ijk
    -0.67
    00000000
    -0.66
    notation
    -0.66
    ¥ŀ
    -0.64
    POSITIVE LOGITS
     McConnell
    1.04
    apes
    0.88
    ments
    0.86
    erson
    0.86
     Mitch
    0.83
     Daniels
    0.78
    ery
    0.77
    agne
    0.76
    hew
    0.75
    uro
    0.75
    Activations Density 0.009%

    No Known Activations