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. 4-RES-JB
    6. 17685
    Prev
    Next
    INDEX
    Explanations

    references to Lightning Network, particularly focusing on different aspects and updates related to its development and deployment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Lightning" or related terms in the context of technology or phenomena

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

    No Comments

    Negative Logits
    ophon
    -0.95
    ais
    -0.84
    sburgh
    -0.84
    aum
    -0.81
    verb
    -0.80
    ublic
    -0.79
    ester
    -0.78
    glers
    -0.78
    alian
    -0.78
    alse
    -0.78
    POSITIVE LOGITS
     bolt
    1.05
     bolts
    0.97
    bolt
    0.90
     lightning
    0.85
     Bolt
    0.84
     skating
    0.81
     Lights
    0.78
     rod
    0.77
     Lightning
    0.77
     Strikes
    0.76
    Activations Density 0.012%

    No Known Activations