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. 16814
    Prev
    Next
    INDEX
    Explanations

    names related to Aung San Suu Kyi

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and entities, particularly those related to Myanmar's 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
    å°Ĩ
    -0.55
     guiActiveUn
    -0.54
     Topics
    -0.54
    Leaks
    -0.54
     equival
    -0.54
     largeDownload
    -0.54
    ellen
    -0.53
    overs
    -0.52
     Beasts
    -0.52
     womb
    -0.51
    POSITIVE LOGITS
    icient
    0.82
    intendent
    0.81
    iman
    0.68
    sembly
    0.67
    uyomi
    0.66
    eton
    0.65
    ylum
    0.64
    oka
    0.64
    pta
    0.62
    imaru
    0.62
    Activations Density 0.132%

    No Known Activations