© 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. 9-RES-JB
    11. 7356
    Prev
    Next
    INDEX
    Explanations

    words related to lungs and respiratory issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lung health and diseases, particularly lung cancer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ezvous
    -0.78
    inosaur
    -0.69
     GOODMAN
    -0.68
    lease
    -0.66
     Templar
    -0.64
     lighthouse
    -0.63
    antine
    -0.62
    */(
    -0.62
    HCR
    -0.62
     Preferred
    -0.61
    POSITIVE LOGITS
    monary
    1.21
     lungs
    0.92
     cavity
    0.89
    nuts
    0.88
     lung
    0.87
     inhal
    0.80
    culosis
    0.79
     asthma
    0.79
    nut
    0.78
    pipe
    0.77
    Activations Density 0.056%

    No Known Activations