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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3137
    Prev
    Next
    INDEX
    Explanations

    mentions of the specific term "Su"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Su-24 bomber aircraft

    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
     directions
    -0.77
     Fiber
    -0.72
     Blumenthal
    -0.68
    naires
    -0.67
     Gutenberg
    -0.66
    eering
    -0.65
     Lyme
    -0.64
    hyde
    -0.62
     rotating
    -0.62
     Ashton
    -0.62
    POSITIVE LOGITS
    arez
    1.08
    pper
    1.07
    icidal
    1.03
    idan
    0.96
    icides
    0.96
    Su
    0.95
    ples
    0.93
    zanne
    0.93
    ppers
    0.91
     Su
    0.90
    Activations Density 0.004%

    No Known Activations