© 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. 2636
    Prev
    Next
    INDEX
    Explanations

    mentions of legal issues, health, and regulatory violations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to dietary supplements and their effects on health

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Kafka
    -1.04
    ttle
    -0.87
     rapp
    -0.86
    raints
    -0.77
    cock
    -0.76
    brush
    -0.73
    nick
    -0.73
    Terror
    -0.72
     Inferno
    -0.71
     Horror
    -0.71
    POSITIVE LOGITS
     vitamin
    1.91
     Vitamin
    1.79
     supplementation
    1.72
     supplements
    1.68
     vitamins
    1.67
    itamin
    1.59
     supplement
    1.49
    amins
    1.45
     creatine
    1.43
     antioxidant
    1.41
    Activations Density 0.209%

    No Known Activations