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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 8611
    Prev
    Next
    INDEX
    Explanations

    words related to cancer

    oai_token-act-pair · gpt-3.5-turbo

    references to cancer and related diseases

    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
    BOOK
    -0.84
    rish
    -0.77
     Helpful
    -0.76
    é¾įåĸļ士
    -0.72
     Enlight
    -0.70
    stanbul
    -0.70
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.70
    worldly
    -0.69
     Polk
    -0.67
    rek
    -0.67
    POSITIVE LOGITS
     cancer
    1.15
    cancer
    1.09
    ous
    1.05
     metast
    1.04
     chemotherapy
    0.95
     diagnosis
    0.91
     cancers
    0.88
     screenings
    0.88
     tumors
    0.88
     Cancer
    0.88
    Activations Density 0.013%

    No Known Activations