© 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. 0-RES-JB
    11. 10460
    Prev
    Next
    INDEX
    Explanations

    words related to tumors

    oai_token-act-pair · gpt-3.5-turbo

    references to tumors 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
     Slovenia
    -0.72
     Sloven
    -0.71
     Eddie
    -0.69
     Folk
    -0.67
    ãĥĥãĤ¯
    -0.66
     stewards
    -0.65
     Esper
    -0.65
     Conway
    -0.63
    ewater
    -0.62
     Des
    -0.61
    POSITIVE LOGITS
     tumor
    3.39
     tum
    2.93
     tumors
    2.72
     metast
    1.27
     cancer
    1.23
     thyroid
    1.22
     lesions
    1.21
     hypothal
    1.15
    cancer
    1.14
     cancers
    1.10
    Activations Density 0.032%

    No Known Activations