© 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. 11-RES-JB
    11. 20758
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Richard" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Richard"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sites
    -0.83
    tical
    -0.72
    iatrics
    -0.72
    ographed
    -0.67
    fare
    -0.66
     Nadu
    -0.64
     emphasis
    -0.63
    days
    -0.63
    culosis
    -0.62
    itness
    -0.62
    POSITIVE LOGITS
     Dawkins
    1.18
     Nixon
    1.11
     Pryor
    0.99
     Stall
    0.94
     Painter
    0.90
     Hof
    0.87
     Wagner
    0.87
     Mellon
    0.84
     Spencer
    0.84
     Simmons
    0.82
    Activations Density 0.034%

    No Known Activations