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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11161
    Prev
    Next
    INDEX
    Explanations

    mentions of refugees and migrants, especially in the context of border crossings and asylum seeking

    oai_token-act-pair · gpt-3.5-turbo

    instances of migration and the movement of refugees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patent
    -0.83
    mson
    -0.78
     Edison
    -0.75
     Earl
    -0.75
    Craft
    -0.73
     Pinball
    -0.73
     patents
    -0.73
    ãĤ¦ãĤ¹
    -0.72
    é¾
    -0.72
     Craft
    -0.72
    POSITIVE LOGITS
     UNHCR
    1.53
     refugees
    1.47
     migrants
    1.42
     fleeing
    1.42
     resettlement
    1.39
     refugee
    1.38
     smugglers
    1.33
     Refugees
    1.28
     humanitarian
    1.27
     arrivals
    1.22
    Activations Density 0.422%

    No Known Activations