© 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. 4-RES-JB
    11. 9299
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of flights

    oai_token-act-pair · gpt-3.5-turbo

    references to flights

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

    No Comments

    Negative Logits
    女
    -0.76
    ortium
    -0.69
    ãĥ¤
    -0.68
    天
    -0.68
    essee
    -0.67
    ãģį
    -0.66
    1920
    -0.65
     regenerate
    -0.63
    selves
    -0.63
     Shinzo
    -0.63
    POSITIVE LOGITS
    crew
    1.03
    plane
    0.97
     Flight
    0.96
     flight
    0.95
     flights
    0.95
    planes
    0.89
     attendants
    0.89
    walk
    0.87
     attendant
    0.86
    deck
    0.81
    Activations Density 0.017%

    No Known Activations