© 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. 17277
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    tentative or uncertain statements

    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
    cies
    -0.88
    arthed
    -0.82
    ament
    -0.79
    lete
    -0.78
    ief
    -0.77
    eme
    -0.77
    zeb
    -0.76
    lisher
    -0.75
    ourse
    -0.75
    oven
    -0.73
    POSITIVE LOGITS
     someday
    0.98
     Acer
    0.70
     SOME
    0.69
     opio
    0.67
     subconscious
    0.67
    haps
    0.66
     sensing
    0.66
     sooner
    0.62
     maybe
    0.62
     unintentionally
    0.61
    Activations Density 0.026%

    No Known Activations