© 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. 10-RES-JB
    11. 16000
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Lew."

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

    references to individuals named "Lew", potentially related to Lewinsky

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.84
     bulls
    -0.72
    CHR
    -0.64
    ||||
    -0.63
     conditioned
    -0.61
     à¨
    -0.61
     vet
    -0.61
     ra
    -0.60
     Shiite
    -0.60
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.59
    POSITIVE LOGITS
    andowski
    1.72
    insky
    1.25
    inski
    1.09
    iston
    0.98
    yers
    0.98
    iak
    0.95
    enstein
    0.95
    die
    0.93
    ellen
    0.92
    ald
    0.92
    Activations Density 0.026%

    No Known Activations