© 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. 22232
    Prev
    Next
    INDEX
    Explanations

    references to pilots or aviation

    oai_token-act-pair · gpt-3.5-turbo

    references to "pilot" as it relates to various contexts, such as projects and programs

    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
    upon
    -0.81
    TOP
    -0.77
     Extrem
    -0.68
    ormon
    -0.68
    Brexit
    -0.67
    llo
    -0.67
     Debor
    -0.66
     Machina
    -0.66
    Newsletter
    -0.65
    rem
    -0.65
    POSITIVE LOGITS
     pilot
    1.06
    wings
    0.97
     Pilot
    0.94
     pilots
    0.85
    selage
    0.83
    isode
    0.81
     episode
    0.81
     whales
    0.79
    ilot
    0.79
     whale
    0.77
    Activations Density 0.013%

    No Known Activations