© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13461
    Prev
    Next
    INDEX
    Explanations

    instances of the word "spying"

    oai_token-act-pair · gpt-3.5-turbo

    references to spying or espionage activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tropical
    -0.77
     NH
    -0.76
     Grande
    -0.75
     Por
    -0.70
     OH
    -0.69
     Akron
    -0.69
    oglobin
    -0.69
     gradient
    -0.69
     Trop
    -0.69
     Fract
    -0.68
    POSITIVE LOGITS
     spying
    3.48
     espionage
    2.84
     spy
    2.64
     spies
    2.63
     eaves
    2.02
    ionage
    1.89
     wiret
    1.73
     Spy
    1.72
     treason
    1.42
     assass
    1.39
    Activations Density 0.028%

    No Known Activations