© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17196
    Prev
    Next
    INDEX
    Explanations

    words related to lack of knowledge or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or a lack of knowledge

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    catentry
    -0.76
     pione
    -0.75
    ogi
    -0.71
    cious
    -0.70
    ccording
    -0.69
    ague
    -0.68
     eleph
    -0.68
    ettel
    -0.67
    rongh
    -0.67
    cedes
    -0.67
    POSITIVE LOGITS
     whatsoever
    1.46
     anymore
    0.89
     nor
    0.70
     Dare
    0.66
     adequately
    0.63
    ifiable
    0.62
     detectable
    0.62
     Caf
    0.61
    èª
    0.61
     Chomsky
    0.61
    Activations Density 0.063%

    No Known Activations