© 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. 9-RES-JB
    11. 23987
    Prev
    Next
    INDEX
    Explanations

    words related to news, events, and explanations

    oai_token-act-pair · gpt-3.5-turbo

    significant names and entities in historical and current events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veggies
    -0.63
     kicker
    -0.59
     dodged
    -0.59
     moms
    -0.57
     woke
    -0.56
     Blazers
    -0.55
    adelphia
    -0.55
     slammed
    -0.55
     kickoff
    -0.54
     popped
    -0.53
    POSITIVE LOGITS
    .[
    1.44
    .(
    1.28
    ."[
    1.24
    .</
    1.22
    *.
    1.21
    .*
    1.20
    .<
    1.14
    ".[
    1.13
    _.
    1.13
     ().
    1.08
    Activations Density 1.083%

    No Known Activations