© 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. 11-RES-JB
    6. 16340
    Prev
    Next
    INDEX
    Explanations

    information related to aircraft and aviation

    oai_token-act-pair · gpt-3.5-turbo

    references to aircraft-related terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wit
    -0.97
    ertodd
    -0.91
    galitarian
    -0.88
     Mori
    -0.85
    Stone
    -0.84
     Witcher
    -0.83
     Fiona
    -0.83
     Snyder
    -0.82
     tamp
    -0.81
    nyder
    -0.81
    POSITIVE LOGITS
     aircraft
    2.18
     aviation
    2.17
     Aircraft
    2.16
     FAA
    2.10
     pilots
    2.07
     airplanes
    2.07
     Aviation
    2.04
     Airbus
    2.00
     Flight
    1.97
     planes
    1.97
    Activations Density 0.837%

    No Known Activations