© 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. 7-RES-JB
    11. 23890
    Prev
    Next
    INDEX
    Explanations

    blood pressure-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cardiovascular health and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.81
    Lens
    -0.79
    UGC
    -0.76
    cott
    -0.75
     Postal
    -0.74
    craft
    -0.73
    rolet
    -0.73
    Iv
    -0.70
    toe
    -0.70
    Rust
    -0.69
    POSITIVE LOGITS
     artery
    1.11
    olesterol
    1.02
     cholesterol
    1.00
     cardiac
    0.98
     hemor
    0.96
     resusc
    0.96
     arteries
    0.95
     cardiovascular
    0.95
     cortisol
    0.94
     heartbeat
    0.93
    Activations Density 0.108%

    No Known Activations