© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 2312
    Prev
    Next
    INDEX
    Explanations

    explanations or descriptions of concepts or events

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases related to understanding and explanations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    inyl
    -0.65
     Nadu
    -0.58
    zan
    -0.51
    termination
    -0.50
    bidden
    -0.50
    panic
    -0.50
    HQ
    -0.49
    adies
    -0.49
     Sabha
    -0.48
    OWN
    -0.48
    POSITIVE LOGITS
     thereof
    1.04
     of
    1.00
     how
    0.72
     OF
    0.70
     why
    0.70
     Of
    0.68
    Of
    0.67
     describing
    0.66
     regarding
    0.66
    of
    0.65
    Activations Density 0.208%

    No Known Activations