© 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. 1-RES-JB
    11. 18815
    Prev
    Next
    INDEX
    Explanations

    fruits, especially apples

    oai_token-act-pair · gpt-3.5-turbo

    specific references to apples

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    interrupted
    -0.79
    uled
    -0.70
    iltr
    -0.70
    enance
    -0.69
    lde
    -0.67
     Registrar
    -0.66
     Lobby
    -0.66
    fram
    -0.63
    uyomi
    -0.63
    LESS
    -0.61
    POSITIVE LOGITS
     apples
    1.66
     apple
    1.23
     cider
    1.20
     oranges
    1.04
    fruit
    1.03
    manship
    1.00
     pies
    0.99
    baum
    0.91
    apple
    0.90
    cakes
    0.89
    Activations Density 0.006%

    No Known Activations