© 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. 7-RES-JB
    11. 14081
    Prev
    Next
    INDEX
    Explanations

    verbs related to health, wellness, and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health effects and medical conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    cknowled
    -0.82
     Huss
    -0.74
     Kahn
    -0.72
     Rosenstein
    -0.71
     Fellowship
    -0.68
    Seg
    -0.68
    Asia
    -0.67
    Mand
    -0.67
    Auth
    -0.66
    Policy
    -0.65
    POSITIVE LOGITS
     digestion
    1.08
     digestive
    1.00
     hardness
    0.95
     carbohyd
    0.95
    icrobial
    0.93
    otropic
    0.91
     serum
    0.90
     toxins
    0.89
     calcium
    0.88
     moisture
    0.85
    Activations Density 0.417%

    No Known Activations