© 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. 10-RES-JB
    11. 13703
    Prev
    Next
    INDEX
    Explanations

    expressions related to skepticism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to skepticism and doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zie
    -0.66
     Occupations
    -0.64
     redund
    -0.61
    apeake
    -0.61
    ounter
    -0.61
    Interstitial
    -0.57
     redistributed
    -0.57
    accompan
    -0.56
    ufact
    -0.56
    interrupted
    -0.56
    POSITIVE LOGITS
    lessly
    1.04
    worthiness
    1.03
    fulness
    0.88
    igious
    0.83
     whether
    0.82
    iably
    0.78
    ingly
    0.77
    ially
    0.75
    bly
    0.73
    icism
    0.71
    Activations Density 0.053%

    No Known Activations