© 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. 2-RES-JB
    11. 12806
    Prev
    Next
    INDEX
    Explanations

    mentions of the Kurdish Peshmerga forces

    oai_token-act-pair · gpt-3.5-turbo

    references to the Peshmerga forces in the context of military engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    razen
    -0.68
     Bohem
    -0.68
     Sleeping
    -0.67
    anity
    -0.67
    Hop
    -0.64
    BOOK
    -0.64
    rified
    -0.63
    elect
    -0.63
    Northern
    -0.63
    oeuv
    -0.61
    POSITIVE LOGITS
    merga
    1.55
     fighters
    0.78
     Forces
    0.75
     airstrikes
    0.73
    istani
    0.72
     fighter
    0.71
     airstrike
    0.71
    Enlarge
    0.69
    conservancy
    0.68
     Leban
    0.68
    Activations Density 0.009%

    No Known Activations