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. 10-RES-JB
    6. 1778
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic relationships and partnerships between countries

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical relationships and alliances

    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
    odder
    -0.79
    rollers
    -0.67
    oway
    -0.66
    lesi
    -0.64
     Shelter
    -0.62
    kson
    -0.60
    ummies
    -0.60
    roll
    -0.60
    erton
    -0.60
    ocalypse
    -0.59
    POSITIVE LOGITS
     mutually
    1.65
     mutual
    1.64
     rivalry
    1.62
     friendship
    1.56
     feud
    1.41
     relationship
    1.41
    relations
    1.40
     interchange
    1.37
     disagreements
    1.37
     friendships
    1.37
    Activations Density 1.545%

    No Known Activations