© 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. 23377
    Prev
    Next
    INDEX
    Explanations

    mentions of aircraft engines, specifically jet engines

    oai_token-act-pair · gpt-3.5-turbo
    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
     NRS
    -0.73
    Constructed
    -0.72
    UGC
    -0.72
    Honest
    -0.68
    éģ
    -0.66
    Republic
    -0.64
     Tablet
    -0.64
    Requires
    -0.63
    Compan
    -0.63
    Beck
    -0.63
    POSITIVE LOGITS
     jet
    1.36
    liner
    1.36
     jets
    1.25
    liners
    1.13
     airliner
    1.13
     planes
    1.03
    jet
    1.02
    oleon
    1.01
     airplanes
    0.99
     plane
    0.96
    Activations Density 0.007%

    No Known Activations