© 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
    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. 3631
    Prev
    Next
    INDEX
    Explanations

    specific terms related to human eyes, eyelids, lashes, and medical eye procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to eyelids and related expressions

    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
    icipated
    -0.79
     Violent
    -0.73
    TAIN
    -0.72
    WER
    -0.72
    FORM
    -0.72
    NOR
    -0.68
    Rich
    -0.68
     Townsend
    -0.66
     ACTION
    -0.65
     Published
    -0.65
    POSITIVE LOGITS
     eyel
    1.44
     lashes
    1.03
    anguage
    1.02
     nodd
    1.00
     mascara
    0.97
     sockets
    0.94
     noses
    0.92
    atonin
    0.91
     hairs
    0.86
     eyebrows
    0.86
    Activations Density 0.006%

    No Known Activations