© 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. 23253
    Prev
    Next
    INDEX
    Explanations

    mentions of uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    tentative modal verbs 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 @ 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
     Kush
    -0.66
    į
    -0.66
    icial
    -0.59
    olis
    -0.57
    rency
    -0.56
    IME
    -0.55
     Palest
    -0.55
    lishes
    -0.54
    atoes
    -0.54
    ATS
    -0.54
    POSITIVE LOGITS
    haps
    1.23
     well
    1.09
    bes
    1.08
    onna
    1.05
    hap
    1.03
     someday
    0.97
     owe
    0.95
    nown
    0.90
     be
    0.89
     have
    0.88
    Activations Density 0.089%

    No Known Activations