© 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. 3-RES-JB
    11. 17111
    Prev
    Next
    INDEX
    Explanations

    specific text abbreviations or codes

    oai_token-act-pair · gpt-3.5-turbo

    references to polling data or survey results related to public opinion

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    âĸĪâĸĪ
    -0.69
     Bhar
    -0.65
     Cassidy
    -0.62
    fruit
    -0.61
    gets
    -0.61
     Hindi
    -0.61
    grass
    -0.61
    rous
    -0.60
     Telegram
    -0.60
    lean
    -0.60
    POSITIVE LOGITS
    senal
    0.97
    agnar
    0.86
    NP
    0.78
    RM
    0.78
    ufact
    0.76
     resil
    0.76
    adeon
    0.76
    bnb
    0.75
    emonic
    0.75
    SEA
    0.74
    Activations Density 0.015%

    No Known Activations