© 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. 0-RES-JB
    11. 4102
    Prev
    Next
    INDEX
    Explanations

    words related to runways or landing strips

    oai_token-act-pair · gpt-3.5-turbo

    terms related to runways and aviation

    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
    achus
    -0.69
     associations
    -0.68
    Ĥª
    -0.65
    fam
    -0.64
     imb
    -0.62
     Dist
    -0.62
     advocates
    -0.62
    actions
    -0.62
    ²¾
    -0.61
    times
    -0.61
    POSITIVE LOGITS
     runway
    4.25
     airst
    1.57
     takeoff
    1.39
    selage
    1.24
     hangar
    1.23
     airport
    1.23
     landfill
    1.12
     treadmill
    1.07
     parachute
    1.03
     coastline
    1.03
    Activations Density 0.013%

    No Known Activations