© 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. 11-RES-JB
    11. 13307
    Prev
    Next
    INDEX
    Explanations

    words related to fuel consumption and efficiency

    oai_token-act-pair · gpt-3.5-turbo

    references to weight and efficiency in the context of aviation or transportation

    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
     disgr
    -0.71
     Paradise
    -0.67
     unmist
    -0.67
     unforgettable
    -0.67
     belonged
    -0.67
     unmarked
    -0.65
     Frankenstein
    -0.64
    ylum
    -0.64
     gle
    -0.64
     existential
    -0.63
    POSITIVE LOGITS
     decrease
    1.45
     decreasing
    1.42
     reducing
    1.41
     decreased
    1.38
    Decre
    1.37
     decreases
    1.37
    Increased
    1.30
     Reduce
    1.29
     Decre
    1.28
     Increased
    1.26
    Activations Density 0.708%

    No Known Activations