© 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. 3039
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "may" indicating possibility or uncertainty

    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
    ciating
    -0.67
    rency
    -0.67
     Palest
    -0.66
    į
    -0.66
    icial
    -0.62
     Kush
    -0.62
     Everywhere
    -0.59
    runtime
    -0.58
    feeding
    -0.57
    pection
    -0.56
    POSITIVE LOGITS
    haps
    1.21
    hap
    1.18
    bes
    1.16
    onna
    1.13
     be
    1.03
     owe
    0.95
     someday
    0.95
     well
    0.92
     have
    0.87
     soon
    0.84
    Activations Density 0.088%

    No Known Activations