© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5103
    Prev
    Next
    INDEX
    Explanations

    references to the World Health Organization (WHO) in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the World Health Organization (WHO) and related key events or terms

    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
     Palin
    -0.79
    Charl
    -0.78
     Cabin
    -0.77
    aska
    -0.76
     McDonnell
    -0.75
     Cavern
    -0.73
     Pul
    -0.72
     Rag
    -0.71
    cair
    -0.69
     Bash
    -0.68
    POSITIVE LOGITS
     WHO
    1.95
     UX
    1.91
    WHO
    1.67
     IoT
    1.65
     keynote
    1.58
     ICO
    1.57
     AMA
    1.42
     TED
    1.27
     FTC
    1.27
     SEO
    1.15
    Activations Density 0.042%

    No Known Activations