© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5825
    Prev
    Next
    INDEX
    Explanations

    proper nouns preceded by "pres" or "Pres"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "presume."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.63
     quot
    -0.63
     mail
    -0.62
     Slov
    -0.62
     Lions
    -0.62
     Rebels
    -0.62
     SAN
    -0.62
     shedding
    -0.61
     autom
    -0.59
     rooting
    -0.57
    POSITIVE LOGITS
    byter
    1.58
    cription
    1.49
    umably
    1.46
    umed
    1.45
    cribed
    1.43
    erving
    1.43
    erved
    1.36
    umption
    1.34
    chool
    1.34
    ervation
    1.32
    Activations Density 0.023%

    No Known Activations