© 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. 1-RES-JB
    11. 2345
    Prev
    Next
    INDEX
    Explanations

    terms related to government agencies and policies regarding immigration

    oai_token-act-pair · gpt-3.5-turbo

    references to immigration and associated governmental agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilts
    -0.83
    robe
    -0.82
    lain
    -0.78
    âĶĢâĶĢ
    -0.77
    outer
    -0.76
    heimer
    -0.76
    arist
    -0.75
    OCK
    -0.74
    private
    -0.73
    chest
    -0.73
    POSITIVE LOGITS
     Immigration
    1.19
     immigration
    1.07
     deported
    0.91
     Detention
    0.88
     Refugees
    0.86
     Traff
    0.81
     visas
    0.81
     Discrimination
    0.80
    immigration
    0.80
    immigrant
    0.80
    Activations Density 0.009%

    No Known Activations