© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4278
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and substances, specifically those related to environmental hazards and health risks

    oai_token-act-pair · gpt-3.5-turbo
    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
    ership
    -0.84
    thumbnails
    -0.78
    gha
    -0.67
     Braves
    -0.66
    CHAT
    -0.63
     Twins
    -0.63
    iversary
    -0.62
     Dhabi
    -0.61
    ļé
    -0.61
    tun
    -0.61
    POSITIVE LOGITS
    mith
    1.05
    ervative
    1.04
    paces
    0.97
    ervatives
    0.95
    pace
    0.95
     emitted
    0.93
     including
    0.91
    ensitive
    0.90
    ystem
    0.89
     affecting
    0.89
    Activations Density 0.208%

    No Known Activations