© 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. 0-RES-JB
    11. 20390
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of cancer

    oai_token-act-pair · gpt-3.5-turbo

    references to cancer and related medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Strongh
    -0.79
     Dahl
    -0.74
     Polk
    -0.73
    aturday
    -0.72
    assian
    -0.71
    rehend
    -0.69
    Ë
    -0.68
    Ã
    -0.67
    riks
    -0.67
     Grip
    -0.66
    POSITIVE LOGITS
     cancer
    3.55
    cancer
    3.03
     Cancer
    2.78
     cancers
    2.71
     leukemia
    2.43
     tumor
    2.16
     carcin
    2.14
     tumors
    2.06
     chemotherapy
    1.93
     metast
    1.71
    Activations Density 0.012%

    No Known Activations