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. 8-RES-JB
    6. 3508
    Prev
    Next
    INDEX
    Explanations

    mentions of minimum wage amounts and related legislation or adjustments

    oai_token-act-pair · gpt-3.5-turbo

    references to minimum wage and related economic policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.80
    projects
    -0.78
    successful
    -0.73
     catalog
    -0.70
    âĹ¼
    -0.70
     Reviews
    -0.70
    ventory
    -0.70
     prophecy
    -0.68
     puzzle
    -0.66
     Catalog
    -0.65
    POSITIVE LOGITS
     Mbps
    0.88
     concess
    0.80
     compulsory
    0.80
    minimum
    0.75
     Adjusted
    0.73
    maximum
    0.72
    afety
    0.72
    Mbps
    0.72
     mandated
    0.71
     cents
    0.71
    Activations Density 0.196%

    No Known Activations