Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19310
    Prev
    Next
    INDEX
    Explanations

    mentions of large numbers of people related to migration, asylum, and refugees

    oai_token-act-pair · gpt-3.5-turbo

    topics related to refugee and migrant statistics and policies

    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
    Cola
    -0.78
    natureconservancy
    -0.75
    opoly
    -0.72
    cour
    -0.71
    wark
    -0.70
    ftime
    -0.70
    ication
    -0.69
    isoft
    -0.68
    omics
    -0.68
     Dealer
    -0.67
    POSITIVE LOGITS
     migrants
    1.59
     refugees
    1.56
     asylum
    1.37
     Rohingya
    1.36
     Syrians
    1.36
     detainees
    1.34
     unaccompanied
    1.31
     Rohing
    1.31
     foreigners
    1.29
     Afghans
    1.28
    Activations Density 0.289%

    No Known Activations