© 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. 9-RES-JB
    11. 2890
    Prev
    Next
    INDEX
    Explanations

    questions or uncertainties about various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express uncertainty or questions about knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.81
    igenous
    -0.74
    herent
    -0.73
    byter
    -0.71
    cible
    -0.68
    ocally
    -0.68
    ibaba
    -0.66
    naissance
    -0.65
    veyard
    -0.64
    Rated
    -0.64
    POSITIVE LOGITS
     how
    0.81
    how
    0.78
     whether
    0.78
     prest
    0.73
     whence
    0.73
     maybe
    0.71
    ?),
    0.70
    âĢ¦)
    0.70
     if
    0.69
    abouts
    0.69
    Activations Density 0.051%

    No Known Activations