© 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. 8-RES-JB
    11. 19277
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Richard"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name Richard

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sites
    -0.83
    atched
    -0.69
    ihar
    -0.69
    ographed
    -0.69
    iatrics
    -0.67
    tical
    -0.65
    cedented
    -0.65
    cule
    -0.63
     Nadu
    -0.62
    around
    -0.62
    POSITIVE LOGITS
     Dawkins
    1.04
     Nixon
    0.97
     Pryor
    0.88
     Simmons
    0.81
     Strauss
    0.77
     Wagner
    0.76
     Johnson
    0.75
     Spencer
    0.75
     Fe
    0.74
     Painter
    0.73
    Activations Density 0.031%

    No Known Activations