© 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. 8-RES-JB
    11. 11027
    Prev
    Next
    INDEX
    Explanations

    questions or uncertainties expressed by the phrase "I don't know."

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ishable
    -0.72
    isco
    -0.69
    coni
    -0.67
    izont
    -0.66
    jam
    -0.64
    attery
    -0.63
    otom
    -0.63
    oided
    -0.63
    ouls
    -0.61
    interstitial
    -0.60
    POSITIVE LOGITS
     how
    0.97
     why
    0.90
     exactly
    0.90
     whether
    0.82
     what
    0.80
     specifics
    0.79
     anymore
    0.79
     enough
    0.75
     WHY
    0.74
     firsthand
    0.73
    Activations Density 0.050%

    No Known Activations