© 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. 0-RES-JB
    11. 1444
    Prev
    Next
    INDEX
    Explanations

    items related to eyeglasses

    oai_token-act-pair · gpt-3.5-turbo

    references to glasses, particularly those related to solar eclipse glasses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anza
    -0.72
     penal
    -0.68
    anie
    -0.66
     exploit
    -0.65
     uncond
    -0.65
     Bomb
    -0.65
    hash
    -0.65
    atal
    -0.63
    orse
    -0.62
    count
    -0.60
    POSITIVE LOGITS
     glasses
    4.12
     sunglasses
    2.45
     goggles
    2.28
     glass
    1.71
     ey
    1.69
     Glass
    1.68
    Glass
    1.57
     lenses
    1.57
    glass
    1.54
    lasses
    1.54
    Activations Density 0.019%

    No Known Activations