© 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. 1-RES-JB
    11. 20058
    Prev
    Next
    INDEX
    Explanations

    terms related to tumors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of tumors and related medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.87
     Dragonbound
    -0.77
    ership
    -0.77
    sers
    -0.76
    âĵĺ
    -0.73
    credit
    -0.68
    ĺ
    -0.68
    ersive
    -0.68
    ña
    -0.68
    erred
    -0.67
    POSITIVE LOGITS
     tumor
    1.34
     tumors
    1.30
     metast
    0.94
     cancer
    0.92
     prostate
    0.88
    cancer
    0.86
     tum
    0.86
     cancers
    0.85
     gland
    0.83
    oidal
    0.78
    Activations Density 0.011%

    No Known Activations