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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 22502
    Prev
    Next
    INDEX
    Explanations

    words related to foot anatomy, specifically toes and heels

    oai_token-act-pair · gpt-3.5-turbo

    terms related to feet and foot anatomy

    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
    HCR
    -0.79
    interrupted
    -0.78
    medium
    -0.74
    ioch
    -0.73
    agents
    -0.72
    infeld
    -0.71
    pmwiki
    -0.71
    edia
    -0.69
     UID
    -0.66
    alcohol
    -0.65
    POSITIVE LOGITS
    toe
    1.59
     toe
    1.43
    bridge
    0.95
     toes
    0.94
    weed
    0.90
     heel
    0.86
    bone
    0.84
    obi
    0.79
    lash
    0.78
     peg
    0.77
    Activations Density 0.006%

    No Known Activations