© 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. 4-RES-JB
    11. 10048
    Prev
    Next
    INDEX
    Explanations

    references to government health departments

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related organizations and terms

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

    No Comments

    Negative Logits
    uble
    -0.78
    cair
    -0.73
    oxide
    -0.73
     slee
    -0.70
    ounter
    -0.68
     goose
    -0.68
    ãĥ£
    -0.68
    encer
    -0.67
    ptions
    -0.67
    unin
    -0.67
    POSITIVE LOGITS
     Care
    1.12
    Care
    1.08
    care
    1.04
     Insurance
    0.90
     Sciences
    0.89
    iest
    0.89
    Health
    0.85
     care
    0.84
     Centers
    0.84
     Advis
    0.84
    Activations Density 0.018%

    No Known Activations