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. 0-RES-JB
    6. 14507
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Lightning Network"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Lightning Network

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.98
     colon
    -0.79
     prof
    -0.70
     laps
    -0.69
     gross
    -0.69
     nep
    -0.69
     disse
    -0.68
     adul
    -0.68
     vill
    -0.68
     mars
    -0.67
    POSITIVE LOGITS
     Lightning
    4.00
     Lighting
    1.67
     Avalanche
    1.51
     lightning
    1.43
     Thunderbolt
    1.41
     Thunder
    1.40
    Thunder
    1.38
     Flames
    1.33
    Light
    1.30
     Sabres
    1.30
    Activations Density 0.017%

    No Known Activations