© 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. 11-RES-JB
    6. 21829
    Prev
    Next
    INDEX
    Explanations

    descriptions or actions related to eyes and gaze

    oai_token-act-pair · gpt-3.5-turbo

    references to eyes and their expressions or states

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.75
    Myth
    -0.71
     carts
    -0.68
     Pros
    -0.68
     Vehicle
    -0.66
     Polit
    -0.64
    èĢħ
    -0.64
    ãĤ¨ãĥ«
    -0.63
    Sov
    -0.63
    acter
    -0.62
    POSITIVE LOGITS
     unfocused
    1.14
     gaze
    1.12
     gazing
    1.09
     widened
    1.06
     widen
    1.06
     sparkling
    1.05
     darkened
    1.05
     narrowed
    1.04
     tint
    1.04
     bright
    1.04
    Activations Density 0.106%

    No Known Activations