© 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. 11-RES-JB
    11. 23085
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with "Under"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "under" in legal or formal contexts

    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
     frivol
    -0.77
     vulner
    -0.71
     whereabouts
    -0.59
     amuse
    -0.57
     bitten
    -0.56
     distur
    -0.56
    ividual
    -0.56
    ospace
    -0.55
     accur
    -0.54
    emia
    -0.54
    POSITIVE LOGITS
    neath
    1.39
    lying
    1.25
    mining
    1.18
    graduate
    1.16
    lining
    1.15
    grad
    1.13
    stand
    1.12
    pins
    1.08
    pin
    1.07
    cover
    1.06
    Activations Density 0.045%

    No Known Activations