© 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. 8-RES-JB
    11. 3347
    Prev
    Next
    INDEX
    Explanations

    references related to flights and aviation

    oai_token-act-pair · gpt-3.5-turbo

    references to specific flights and flight numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¤
    -0.69
    selves
    -0.69
    othe
    -0.69
    stown
    -0.64
    kai
    -0.63
    essee
    -0.61
    女
    -0.61
     Jah
    -0.61
    orkshire
    -0.61
     Nadu
    -0.60
    POSITIVE LOGITS
     attendant
    1.04
    crew
    1.03
     attendants
    1.02
    plane
    0.93
     simulator
    0.93
    mares
    0.93
     Flight
    0.90
    planes
    0.86
    engers
    0.82
    walk
    0.81
    Activations Density 0.018%

    No Known Activations