© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    phrases related to immigration

    oai_token-act-pair · gpt-3.5-turbo

    words related to immigrants and migration issues

    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
    awed
    -0.93
    aws
    -0.91
    orem
    -0.90
    creen
    -0.89
    uits
    -0.88
    aurus
    -0.86
    İĭ
    -0.83
    uden
    -0.83
    peak
    -0.82
    amina
    -0.82
    POSITIVE LOGITS
     immigrant
    1.02
     Worker
    0.92
     migrant
    0.90
     visas
    0.86
    istani
    0.81
     Communities
    0.80
     visa
    0.78
     communities
    0.76
     tract
    0.73
    immigrant
    0.72
    Activations Density 0.010%

    No Known Activations