© 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 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. 8-RES-JB
    11. 16069
    Prev
    Next
    INDEX
    Explanations

    information related to health risks and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to health risks and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.88
    DragonMagazine
    -0.83
     Collider
    -0.75
    Clock
    -0.74
    å°Ĩ
    -0.72
    notations
    -0.71
    framework
    -0.71
    liga
    -0.70
    Enlarge
    -0.70
    artist
    -0.70
    POSITIVE LOGITS
     disease
    1.18
     cardiovascular
    1.16
     diseases
    1.14
     illness
    1.14
     infection
    1.12
     relapse
    1.09
     mortality
    1.09
     adverse
    1.08
     miscarriage
    1.08
     depression
    1.06
    Activations Density 0.189%

    No Known Activations