© 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. 9-RES-JB
    11. 3266
    Prev
    Next
    INDEX
    Explanations

    airline-related terms, with a focus on American Airlines

    oai_token-act-pair · gpt-3.5-turbo

    references to airline names and flights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.70
    hunt
    -0.67
    olithic
    -0.67
    arios
    -0.65
    icle
    -0.65
    kai
    -0.65
     Jah
    -0.65
    olith
    -0.64
    esville
    -0.64
     Tate
    -0.62
    POSITIVE LOGITS
     Airlines
    1.07
     Flight
    1.05
     flight
    0.98
     passenger
    0.98
     passengers
    0.97
     flights
    0.97
     airlines
    0.89
     hangar
    0.85
     Emirates
    0.83
     pilots
    0.83
    Activations Density 0.052%

    No Known Activations