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. 11-RES-JB
    6. 19461
    Prev
    Next
    INDEX
    Explanations

    mentions of India or things related to India

    oai_token-act-pair · gpt-3.5-turbo

    references to India and its political context

    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
    Weiss
    -0.91
    Winter
    -0.90
     Sounders
    -0.85
    lando
    -0.84
    UFC
    -0.79
     Welch
    -0.79
    ĨĴ
    -0.78
     cones
    -0.78
    paio
    -0.77
     Falcon
    -0.77
    POSITIVE LOGITS
     India
    2.28
    India
    2.26
     Indian
    2.11
    Indian
    2.09
     Hindi
    2.05
     Hindu
    2.03
     Gujar
    1.98
     Delhi
    1.94
     Modi
    1.93
     Mumbai
    1.91
    Activations Density 0.738%

    No Known Activations