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. 8818
    Prev
    Next
    INDEX
    Explanations

    references to the Euro currency

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the euro currency

    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
     Richards
    -0.77
    RECT
    -0.73
     Hawkins
    -0.71
     Garland
    -0.69
     Seymour
    -0.67
     Garrison
    -0.66
    ulla
    -0.66
    Bot
    -0.65
    etch
    -0.65
    '>
    -0.65
    POSITIVE LOGITS
     euro
    3.78
    euro
    2.71
     Euro
    2.35
     eurozone
    2.27
    Euro
    2.25
     euros
    2.24
     EUR
    2.08
     Euros
    1.89
     franc
    1.83
     EU
    1.64
    Activations Density 0.012%

    No Known Activations