© 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. 2-RES-JB
    11. 1009
    Prev
    Next
    INDEX
    Explanations

    the word "refugees"

    oai_token-act-pair · gpt-4-turbo

    terms related to refugees

    oai_token-act-pair · gpt-3.5-turbo

    references to refugees and related humanitarian topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snipp
    -0.75
    cor
    -0.73
    ATA
    -0.72
    )=(
    -0.72
    à¸
    -0.71
    efer
    -0.70
    tone
    -0.70
    orp
    -0.69
    Owner
    -0.69
    NC
    -0.68
    POSITIVE LOGITS
     refugees
    1.47
     Refugees
    1.47
     refugee
    1.21
     Refugee
    1.14
     orphans
    1.12
     resettlement
    1.07
     fleeing
    1.03
     asylum
    1.03
     UNHCR
    0.96
     migrants
    0.95
    Activations Density 0.020%

    No Known Activations