© 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. 10416
    Prev
    Next
    INDEX
    Explanations

    names or references to the name "Craig"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Craig."

    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
    lucent
    -0.71
     Seah
    -0.70
    ç¥ŀ
    -0.69
    kHz
    -0.65
    catentry
    -0.64
    llor
    -0.63
     Curiosity
    -0.63
    mble
    -0.63
    escal
    -0.61
     Watergate
    -0.61
    POSITIVE LOGITS
     Craig
    1.24
    Craig
    1.09
     Thomson
    0.90
     Dani
    0.81
     Wright
    0.78
    sonian
    0.75
     Petersen
    0.73
     Travis
    0.73
     Smith
    0.73
    STON
    0.73
    Activations Density 0.006%

    No Known Activations