© 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. 12-RES-JB
    11. 5016
    Prev
    Next
    INDEX
    Explanations

    the word "weight" or phrases related to weight-related activities

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

    references to weight and weight-related concepts

    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
    etheless
    -0.71
    cffffcc
    -0.66
     Brist
    -0.63
     FE
    -0.62
    selves
    -0.61
    RPG
    -0.61
    uber
    -0.61
     Myster
    -0.61
     Outbreak
    -0.60
    opsis
    -0.60
    POSITIVE LOGITS
    lifting
    1.45
    lif
    1.22
    lessness
    1.06
    loss
    1.03
     loss
    0.90
     gain
    0.90
    iless
    0.87
     lifting
    0.86
    bearing
    0.85
    classes
    0.83
    Activations Density 0.042%

    No Known Activations