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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 11970
    Prev
    Next
    INDEX
    Explanations

    names or references to the character "Tyrone"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Tyrion from the "Game of Thrones" series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ou
    -0.80
    erer
    -0.72
    erers
    -0.70
     doub
    -0.65
     Zot
    -0.63
     seams
    -0.63
    ering
    -0.63
     Papua
    -0.62
    ãĤ¤ãĥĪ
    -0.61
    leeve
    -0.60
    POSITIVE LOGITS
    rha
    1.22
    rh
    0.99
    anny
    0.97
    andom
    0.88
    thur
    0.87
    én
    0.84
    rr
    0.82
    terday
    0.81
    azines
    0.80
    antes
    0.78
    Activations Density 0.038%

    No Known Activations