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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 18565
    Prev
    Next
    INDEX
    Explanations

    references to immigration, immigrants, and related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to immigrants and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.87
    idges
    -0.87
    é¾
    -0.81
    ovember
    -0.80
    ģĸ
    -0.76
    ategory
    -0.75
    ival
    -0.73
    iencies
    -0.73
    ilde
    -0.73
     ellipt
    -0.70
    POSITIVE LOGITS
     deported
    1.11
     immigrants
    1.01
     visas
    0.99
     residing
    0.95
     arriving
    0.94
     fleeing
    0.94
     apprehended
    0.90
     detained
    0.90
     visa
    0.90
     deportation
    0.89
    Activations Density 0.062%

    No Known Activations