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. 6-RES-JB
    6. 3148
    Prev
    Next
    INDEX
    Explanations

    numerical mentions of amounts of money in euros

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary values, specifically in euros

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.82
     Defin
    -0.76
    eer
    -0.71
    Discussion
    -0.71
     Peb
    -0.71
    ITNESS
    -0.70
     Siber
    -0.70
    ãĤ¨ãĥ«
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
     Flavoring
    -0.68
    POSITIVE LOGITS
     (£
    0.87
     ($
    0.81
    ochet
    0.79
     âĤ¬
    0.73
    akis
    0.72
    ilateral
    0.71
     Hollande
    0.70
    imeter
    0.69
    kas
    0.69
    coni
    0.69
    Activations Density 0.012%

    No Known Activations