© 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. 11-RES-JB
    11. 10101
    Prev
    Next
    INDEX
    Explanations

    information related to infectious diseases and viruses

    oai_token-act-pair · gpt-3.5-turbo

    references to contagious viruses and their transmission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.90
    HUD
    -0.84
    iture
    -0.84
    displayText
    -0.80
     srfAttach
    -0.79
    DCS
    -0.78
    dash
    -0.78
    gpu
    -0.75
    cknow
    -0.74
    leans
    -0.73
    POSITIVE LOGITS
     viruses
    1.57
     virus
    1.55
     infection
    1.54
     influenza
    1.51
     infections
    1.44
     pathogens
    1.40
     measles
    1.39
     hepatitis
    1.36
     herpes
    1.36
     Zika
    1.35
    Activations Density 0.235%

    No Known Activations