© 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. 2-RES-JB
    11. 12020
    Prev
    Next
    INDEX
    Explanations

    mentions of heart attacks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to heart attacks and associated medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.74
    HOU
    -0.71
    DEM
    -0.67
    soDeliveryDate
    -0.66
    =-=-
    -0.66
     Vend
    -0.66
    âĸij
    -0.65
    åº
    -0.65
     Purch
    -0.65
     Opportunity
    -0.64
    POSITIVE LOGITS
    rosis
    1.29
     inflammation
    1.18
     disorders
    1.16
     arthritis
    1.12
    clerosis
    1.10
     dementia
    1.09
     neurological
    1.09
     asthma
    1.08
     lymph
    1.08
     artery
    1.07
    Activations Density 0.216%

    No Known Activations