© 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. 2484
    Prev
    Next
    INDEX
    Explanations

    references to political and social issues, including actions taken by political figures and societal challenges

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

    references to governmental actions and policies related to whistleblowers and national security

    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
     furry
    -0.55
     warr
    -0.51
     rabbit
    -0.50
     ensu
    -0.49
    guyen
    -0.48
     welf
    -0.47
     humour
    -0.47
     tv
    -0.47
     selfies
    -0.46
     toile
    -0.46
    POSITIVE LOGITS
    .""
    1.28
    .")
    1.25
     ."
    1.25
    ."[
    1.22
    .'"
    1.13
    ;"
    1.12
    .;
    1.09
    ";
    1.08
    ."
    1.05
    .}
    1.04
    Activations Density 1.524%

    No Known Activations