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. 21799
    Prev
    Next
    INDEX
    Explanations

    mentions of discussions or debates about single-payer health care systems

    oai_token-act-pair · gpt-3.5-turbo

    references to single-payer health care systems

    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
     ta
    -0.66
     faded
    -0.66
     distance
    -0.65
     dark
    -0.65
     twisted
    -0.64
     inf
    -0.64
     blurred
    -0.64
    ija
    -0.63
     smooth
    -0.63
     fog
    -0.63
    POSITIVE LOGITS
    payer
    4.53
    payers
    3.87
    paying
    1.25
     taxpayer
    1.20
    exempt
    1.09
    naire
    1.08
     taxpayers
    1.07
    payment
    1.01
    backer
    0.99
    pees
    0.98
    Activations Density 0.013%

    No Known Activations