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. 1-RES-JB
    6. 15359
    Prev
    Next
    INDEX
    Explanations

    references to large quantities or amounts of money

    oai_token-act-pair · gpt-3.5-turbo

    references to large numerical values, particularly millions and billions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -0.71
     outlawed
    -0.62
     chilling
    -0.62
     directions
    -0.62
     conditioning
    -0.61
    ional
    -0.60
    RW
    -0.60
     BJ
    -0.60
     stern
    -0.59
    ded
    -0.58
    POSITIVE LOGITS
    aire
    1.11
    aires
    1.05
     Million
    0.94
    agy
    0.86
     Dollar
    0.82
    naire
    0.79
    arov
    0.77
    Year
    0.74
    acre
    0.74
     Millions
    0.72
    Activations Density 0.007%

    No Known Activations