© 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 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. 4-RES-JB
    11. 6966
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Craig"

    oai_token-act-pair · gpt-3.5-turbo

    mentions 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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.75
     eleph
    -0.75
    catentry
    -0.74
    ç¥ŀ
    -0.69
     Seah
    -0.68
     Glob
    -0.68
    iors
    -0.67
    ktop
    -0.65
    ortunately
    -0.65
     Curiosity
    -0.62
    POSITIVE LOGITS
     Craig
    0.83
     Thomson
    0.83
    uda
    0.79
    ards
    0.76
     Dani
    0.73
     Wright
    0.73
     Melvin
    0.73
    Craig
    0.72
    mere
    0.71
    imar
    0.71
    Activations Density 0.011%

    No Known Activations