© 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. 6475
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or lack of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express uncertainty or questioning about specifics

    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
     Advertisement
    -0.74
    ULTS
    -0.63
    HT
    -0.59
    ocard
    -0.58
     Definitely
    -0.56
    Otherwise
    -0.56
    ANE
    -0.56
     greatly
    -0.56
    ELD
    -0.56
    senal
    -0.55
    POSITIVE LOGITS
     how
    1.02
    what
    1.01
     HOW
    0.99
    why
    0.98
     WHY
    0.97
     why
    0.95
     what
    0.94
     whats
    0.89
    where
    0.84
     WHAT
    0.80
    Activations Density 0.034%

    No Known Activations