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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9087
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific cryptocurrency, Litecoin

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cryptocurrencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Faul
    -0.81
     Eisenhower
    -0.69
     Borders
    -0.69
     Baxter
    -0.69
     Bauer
    -0.68
    NEY
    -0.67
     CHO
    -0.67
     ABE
    -0.67
     Schr
    -0.66
     narrator
    -0.66
    POSITIVE LOGITS
    coins
    0.98
    coin
    0.97
    nect
    0.96
    regate
    0.95
    currency
    0.95
    apult
    0.92
    urrency
    0.91
    urrencies
    0.89
    rencies
    0.89
    bitcoin
    0.85
    Activations Density 0.012%

    No Known Activations