© 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 EvalsExportsinterp-engineNEWAPI 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. 23149
    Prev
    Next
    INDEX
    Explanations

    mentions of various diseases, notably cancer

    oai_token-act-pair · gpt-3.5-turbo

    references to cancer and related medical topics

    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
    BOOK
    -0.87
    stanbul
    -0.85
    worldly
    -0.79
    */(
    -0.75
    theless
    -0.74
    rish
    -0.73
    mble
    -0.72
    Snap
    -0.72
    Atl
    -0.69
    ership
    -0.68
    POSITIVE LOGITS
    ous
    1.26
     diagnosis
    1.02
     cancer
    1.01
     chemotherapy
    1.00
     metast
    0.98
     screenings
    0.96
     diagnoses
    0.93
     tumors
    0.91
     survivor
    0.91
    cancer
    0.91
    Activations Density 0.041%

    No Known Activations