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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3851
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations or entities related to health

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coni
    -0.73
    âĸ¬
    -0.68
    venants
    -0.67
     tongues
    -0.65
     Horn
    -0.64
    umar
    -0.64
    ãĤ©
    -0.64
     goose
    -0.62
     Gibbs
    -0.62
    Ń·
    -0.62
    POSITIVE LOGITS
    Health
    1.13
     Care
    1.11
    care
    1.10
    Care
    1.06
     Health
    0.98
     care
    0.96
    aceutical
    0.93
    iest
    0.90
    health
    0.84
    hazard
    0.82
    Activations Density 0.011%

    No Known Activations