© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 20403
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Simpson"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Simpson" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    href
    -0.79
    WIND
    -0.74
    HAHAHAHA
    -0.71
    inventoryQuantity
    -0.70
    places
    -0.67
    EEK
    -0.64
    warm
    -0.63
    ads
    -0.63
    aird
    -0.63
    arians
    -0.62
    POSITIVE LOGITS
     Simpson
    1.44
    pson
    1.01
    sonian
    0.88
    ertodd
    0.81
    ufact
    0.79
    psons
    0.75
    oshenko
    0.75
    inez
    0.72
    querque
    0.71
     Clause
    0.70
    Activations Density 0.008%

    No Known Activations