© 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. 1-RES-JB
    11. 10422
    Prev
    Next
    INDEX
    Explanations

    the word "Lex" or variations of it, such as "Lex Luthor" and "Lexie"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Lex" or related names

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.79
    ailable
    -0.77
    ño
    -0.73
    renheit
    -0.69
    ounty
    -0.68
    resents
    -0.66
    cffffcc
    -0.65
    atcher
    -0.64
    udder
    -0.63
    jri
    -0.63
    POSITIVE LOGITS
     Luthor
    1.33
     Lex
    1.18
    Lex
    1.17
     lex
    1.02
    iom
    0.95
    iton
    0.93
     Machina
    0.89
    iazep
    0.87
     Lug
    0.85
    Benz
    0.85
    Activations Density 0.003%

    No Known Activations