© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9899
    Prev
    Next
    INDEX
    Explanations

    words related to the word "ok."

    oai_token-act-pair · gpt-3.5-turbo

    the word "ok" and its variations in different 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
     textbooks
    -0.61
    bugs
    -0.60
     missionaries
    -0.59
    ebook
    -0.59
    ordinary
    -0.59
    WHERE
    -0.58
     Tempest
    -0.58
     lav
    -0.57
     seams
    -0.56
     Sparkle
    -0.56
    POSITIVE LOGITS
    hov
    1.27
    lass
    1.13
    unin
    1.11
    nown
    1.04
    lahoma
    1.02
    htar
    1.00
    owski
    0.98
    uyomi
    0.98
    hari
    0.97
    alore
    0.96
    Activations Density 0.028%

    No Known Activations