© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14204
    Prev
    Next
    INDEX
    Explanations

    Italian words or names and their variations, with a particular emphasis on "li"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "li" or words containing "li."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    lain
    -0.96
    spin
    -0.75
    specified
    -0.70
    landish
    -0.67
    lins
    -0.66
    theless
    -0.65
    worthiness
    -0.64
    lined
    -0.63
    lift
    -0.63
    */(
    -0.62
    POSITIVE LOGITS
    Äĩ
    1.28
    ère
    1.06
    plom
    1.04
    emi
    1.04
    ya
    1.03
    pper
    1.02
    yah
    1.01
    ón
    0.96
    orno
    0.95
    essen
    0.95
    Activations Density 0.124%

    No Known Activations