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. 21221
    Prev
    Next
    INDEX
    Explanations

    mentions of specific monetary amounts in the form of coins

    oai_token-act-pair · gpt-3.5-turbo

    references to specific small denominations of currency, particularly dimes and pennies

    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
    lov
    -0.86
    LOD
    -0.80
    âĶĢ
    -0.80
    Ve
    -0.74
     Mastery
    -0.74
    arts
    -0.72
    Vers
    -0.71
    \\\\\\\\\\\\\\\\
    -0.69
     Activ
    -0.69
    assi
    -0.68
    POSITIVE LOGITS
     penny
    3.66
     dime
    3.49
     Penny
    2.19
     nickel
    2.18
     penn
    1.62
     dollar
    1.53
    dollar
    1.26
     Dollar
    1.21
     payday
    1.15
     dollars
    1.12
    Activations Density 0.018%

    No Known Activations