© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10748
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "visa"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of visa-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worn
    -0.68
    sonian
    -0.68
     Yards
    -0.67
    MpServer
    -0.67
    ribution
    -0.66
    ocrat
    -0.65
    wolf
    -0.64
    ilde
    -0.63
     willpower
    -0.62
     Measure
    -0.62
    POSITIVE LOGITS
     versa
    1.36
     visas
    1.30
     visa
    1.27
     waiver
    0.85
    uana
    0.80
     waivers
    0.79
     nationals
    0.77
    ptin
    0.74
     holders
    0.72
     abroad
    0.71
    Activations Density 0.008%

    No Known Activations