© 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. 11-RES-JB
    11. 22082
    Prev
    Next
    INDEX
    Explanations

    information related to health conditions and risks associated with cholesterol levels, blood pressure, heart rates, and various diseases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cholesterol and various health conditions associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selage
    -0.77
    Revolution
    -0.76
    ctor
    -0.75
    outhern
    -0.74
    ateurs
    -0.72
    idable
    -0.72
    Sham
    -0.72
    herer
    -0.72
    Deal
    -0.72
    bots
    -0.70
    POSITIVE LOGITS
     triglycer
    1.28
     LDL
    1.27
     cortisol
    1.24
     cholesterol
    1.23
     risk
    1.21
     HDL
    1.19
     incidence
    1.14
     mortality
    1.13
     urinary
    1.12
     levels
    1.12
    Activations Density 0.099%

    No Known Activations