© 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. 8-RES-JB
    11. 6337
    Prev
    Next
    INDEX
    Explanations

    information related to health conditions, treatments, and medical studies

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the health implications of smoking and related medical conditions

    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
     Franch
    -0.93
    Accessory
    -0.80
    Business
    -0.78
    Guest
    -0.76
    Assembly
    -0.75
    Chain
    -0.74
    Politics
    -0.72
     symbolism
    -0.72
    tainment
    -0.71
    ãģĨ
    -0.70
    POSITIVE LOGITS
     chronically
    1.28
     clinically
    1.13
     diagnosed
    1.10
    opausal
    1.10
     allergic
    1.08
     hormone
    1.07
     deficient
    1.07
     diabetic
    1.07
     symptoms
    1.04
     remission
    1.04
    Activations Density 0.433%

    No Known Activations