© 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. 4925
    Prev
    Next
    INDEX
    Explanations

    the term "Dis" followed by a word

    oai_token-act-pair · gpt-3.5-turbo

    variations of the prefix "Dis" in a variety of contexts, often indicating negation or reversal

    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
     ages
    -0.66
     Deer
    -0.60
     Boxing
    -0.59
     Hunt
    -0.59
     whisper
    -0.59
     Upton
    -0.58
     formula
    -0.58
     Whale
    -0.56
     Mint
    -0.56
    DragonMagazine
    -0.55
    POSITIVE LOGITS
    cipl
    1.48
    claimer
    1.39
    ruption
    1.37
    ciplinary
    1.35
    rupt
    1.32
    cipline
    1.31
    ciples
    1.29
    puted
    1.29
    enfranch
    1.29
    rupted
    1.28
    Activations Density 0.015%

    No Known Activations