© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11585
    Prev
    Next
    INDEX
    Explanations

    keywords related to flights and air travel

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "flights."

    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
    uka
    -0.72
    eth
    -0.71
    stone
    -0.65
    cloth
    -0.65
    +++
    -0.64
    mouth
    -0.64
    zo
    -0.62
    acea
    -0.61
    anna
    -0.61
     gem
    -0.60
    POSITIVE LOGITS
     flights
    3.89
     flight
    2.23
     planes
    1.98
     airlines
    1.87
     Flight
    1.85
    Flight
    1.84
     airplanes
    1.81
     airports
    1.66
    flight
    1.64
     trips
    1.61
    Activations Density 0.013%

    No Known Activations