© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21751
    Prev
    Next
    INDEX
    Explanations

    words related to the medical condition of lungs, such as "lung cancer" and "lung infection."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lung health and disease

    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
     Templar
    -0.73
    */(
    -0.72
     GOODMAN
    -0.69
     Ake
    -0.68
    actionDate
    -0.67
     CoC
    -0.66
    Ô
    -0.66
    CLASSIFIED
    -0.64
    ZI
    -0.63
    Square
    -0.62
    POSITIVE LOGITS
    monary
    1.08
    nuts
    0.99
     lung
    0.97
     lungs
    0.87
     cavity
    0.86
    nut
    0.84
    pipe
    0.79
     Lung
    0.79
    bons
    0.79
     cancer
    0.78
    Activations Density 0.033%

    No Known Activations