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. 1-RES-JB
    6. 24536
    Prev
    Next
    INDEX
    Explanations

    the name "Tyrone" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character "Tyr" and related figures in the context of narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ou
    -0.79
    âĸ¬âĸ¬
    -0.77
    Offline
    -0.72
    )=(
    -0.71
     largeDownload
    -0.70
     Physicians
    -0.69
    Merit
    -0.68
    ãģ¦
    -0.66
    TERN
    -0.65
    manship
    -0.65
    POSITIVE LOGITS
     tyr
    1.21
     Tyr
    1.19
    anny
    0.95
    rell
    0.92
    rible
    0.89
     Lann
    0.87
    oshenko
    0.86
    acious
    0.83
    romancer
    0.78
    idal
    0.76
    Activations Density 0.008%

    No Known Activations