© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5608
    Prev
    Next
    INDEX
    Explanations

    words related to confusion or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "confusion" and related terms expressing uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icle
    -0.73
    estone
    -0.73
    icles
    -0.66
    nesium
    -0.65
    ĻĤ
    -0.64
    Interstitial
    -0.63
    har
    -0.63
    artifacts
    -0.62
    amins
    -0.61
    ovy
    -0.61
    POSITIVE LOGITS
     arose
    0.93
     stemming
    0.93
    lessness
    0.89
     arising
    0.87
     arises
    0.86
     regarding
    0.84
    fulness
    0.80
    lessly
    0.79
    FUL
    0.76
     arise
    0.76
    Activations Density 0.086%

    No Known Activations