© 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. 23203
    Prev
    Next
    INDEX
    Explanations

    terms related to various diseases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to diseases and health 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
    displayText
    -0.68
     Truck
    -0.65
     concession
    -0.63
     gallery
    -0.62
    assy
    -0.61
    board
    -0.61
     tweet
    -0.60
     final
    -0.59
     figure
    -0.58
     statue
    -0.58
    POSITIVE LOGITS
     diseases
    3.24
     Diseases
    2.44
     illnesses
    2.15
     ailments
    2.05
     pathogens
    1.82
     cancers
    1.80
     disorders
    1.74
     infections
    1.63
     disease
    1.53
     medicines
    1.53
    Activations Density 0.011%

    No Known Activations