© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 599
    Prev
    Next
    INDEX
    Explanations

    mentions of physiological health indicators related to the cardiovascular system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to blood pressure and circulation health

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

    No Comments

    Negative Logits
    wcsstore
    -0.86
    é¾
    -0.84
    CAST
    -0.83
    oral
    -0.79
    Company
    -0.75
    cott
    -0.75
    ãĤ©
    -0.75
    cash
    -0.74
    NL
    -0.73
    Rust
    -0.72
    POSITIVE LOGITS
     cholesterol
    1.03
    olesterol
    0.98
     disorders
    0.92
    ysis
    0.90
     artery
    0.90
     disorder
    0.88
     arteries
    0.87
     hemor
    0.86
     cardiovascular
    0.85
     hypertension
    0.83
    Activations Density 0.034%

    No Known Activations