© 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. 11-RES-JB
    11. 21635
    Prev
    Next
    INDEX
    Explanations

    words indicating uncertainty or ignorance

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mere
    -0.84
    Ĭ±
    -0.77
     Victim
    -0.61
    ¯
    -0.61
    £ı
    -0.60
    quad
    -0.60
    prev
    -0.60
     aiding
    -0.57
    ridge
    -0.57
    天
    -0.57
    POSITIVE LOGITS
     realise
    1.22
     realize
    1.19
     bother
    1.09
     know
    1.08
    epad
    0.98
     realised
    0.96
     expect
    0.95
    want
    0.95
     remember
    0.95
     KNOW
    0.93
    Activations Density 0.140%

    No Known Activations