© 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. 1-RES-JB
    11. 13459
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "immigration."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to immigration

    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
    ENA
    -0.80
    姫
    -0.76
    ches
    -0.71
     Flavoring
    -0.71
    POSE
    -0.70
    orah
    -0.70
    IVES
    -0.69
    aple
    -0.68
    verages
    -0.67
    ilts
    -0.67
    POSITIVE LOGITS
     immigration
    1.30
    immigration
    1.06
     visas
    1.04
     detention
    1.00
     deported
    1.00
     deportation
    0.99
    immigrant
    0.91
     immigrants
    0.89
     enforcement
    0.89
     screening
    0.89
    Activations Density 0.015%

    No Known Activations