© 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. 4-RES-JB
    11. 10040
    Prev
    Next
    INDEX
    Explanations

    references to different types, features, and uses of shoes

    oai_token-act-pair · gpt-3.5-turbo

    references to shoes and related terminology

    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
    CLASSIFIED
    -0.74
     Experimental
    -0.68
    ITIES
    -0.67
     Modes
    -0.66
    imens
    -0.66
    anooga
    -0.63
     MacArthur
    -0.63
    isson
    -0.63
    ities
    -0.63
     McDonnell
    -0.63
    POSITIVE LOGITS
    toe
    1.03
     heel
    0.98
    horn
    0.94
     shoe
    0.91
    bag
    0.80
    loo
    0.78
    oos
    0.77
     sock
    0.77
     toe
    0.76
     strap
    0.75
    Activations Density 0.014%

    No Known Activations