Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 6639
    Prev
    Next
    INDEX
    Explanations

    mentions of specific groups of people or individuals in the context of health or medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or populations of people, particularly in a medical or research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥķãĤ©
    -0.80
    Chain
    -0.75
    Oracle
    -0.74
    é»Ĵ
    -0.73
    TPS
    -0.72
     Syndicate
    -0.72
    Rules
    -0.71
    Platform
    -0.71
    Freedom
    -0.69
    FTWARE
    -0.69
    POSITIVE LOGITS
     diagnosed
    1.07
     ingested
    1.00
     clinicians
    0.95
     vaccinated
    0.93
     hospitalized
    0.93
     clinically
    0.93
     patients
    0.91
     aged
    0.90
     asthma
    0.90
     enrolled
    0.90
    Activations Density 0.174%

    No Known Activations