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. 9-RES-JB
    6. 3933
    Prev
    Next
    INDEX
    Explanations

    numbers, statistics, and financial terms related to taxes and government income

    oai_token-act-pair · gpt-3.5-turbo

    financial statistics and comparisons regarding taxes and income

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     playthrough
    -0.70
     coma
    -0.64
     ensued
    -0.62
    edi
    -0.62
     confir
    -0.60
    aders
    -0.60
     encount
    -0.58
    icter
    -0.57
    knit
    -0.56
    activ
    -0.55
    POSITIVE LOGITS
     annually
    0.92
     fewer
    0.88
     GDP
    0.87
     differently
    0.78
     annual
    0.76
     equivalents
    0.76
     per
    0.76
     twice
    0.75
     surplus
    0.74
     average
    0.74
    Activations Density 0.325%

    No Known Activations