Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23586
    Prev
    Next
    INDEX
    Explanations

    phrases related to aviation and pilots

    oai_token-act-pair · gpt-3.5-turbo

    references to pilots and aviation-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.81
     Vit
    -0.77
     Territories
    -0.76
     Vita
    -0.71
     Democr
    -0.71
     Debor
    -0.69
    âĸº
    -0.67
     Nare
    -0.67
     CPS
    -0.66
     Baptist
    -0.66
    POSITIVE LOGITS
     pilots
    1.34
    selage
    1.11
     pilot
    1.09
    wings
    1.08
     cockpit
    1.05
    ilot
    0.95
     certific
    0.92
     hangar
    0.91
     squadron
    0.90
     ace
    0.89
    Activations Density 0.007%

    No Known Activations