© 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. 1-RES-JB
    11. 11554
    Prev
    Next
    INDEX
    Explanations

    questions or statements with a questioning tone

    oai_token-act-pair · gpt-3.5-turbo

    questions and expressions of uncertainty or wonder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.58
    dayName
    -0.54
    susp
    -0.49
    1983
    -0.49
     vacated
    -0.49
    1981
    -0.49
    thumbnails
    -0.48
    RF
    -0.47
    Vers
    -0.46
    1974
    -0.45
    POSITIVE LOGITS
    oooooooooooooooo
    0.72
    ntil
    0.72
    yss
    0.65
    ̶
    0.59
    vana
    0.57
    udic
    0.56
    eday
    0.56
    oooooooo
    0.55
     surprises
    0.54
     hindsight
    0.54
    Activations Density 4.954%

    No Known Activations