© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16293
    Prev
    Next
    INDEX
    Explanations

    keywords related to the airline industry, particularly focusing on the term "Air" followed by specific airline-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to "Air" followed by numerical designators related to military or aviation contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.82
    iddling
    -0.69
    eters
    -0.65
    ection
    -0.65
    ktop
    -0.64
    âģ
    -0.64
     sund
    -0.64
     BUS
    -0.64
     Sanford
    -0.64
     ç¥ŀ
    -0.63
    POSITIVE LOGITS
    plane
    1.03
    planes
    0.95
     Air
    0.90
    Air
    0.87
    waves
    0.86
    zac
    0.85
     Force
    0.82
    bnb
    0.79
    borne
    0.77
     Flight
    0.76
    Activations Density 0.016%

    No Known Activations