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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9429
    Prev
    Next
    INDEX
    Explanations

    references to refugee-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to refugees and the refugee crisis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abeth
    -0.85
    phalt
    -0.81
    paio
    -0.80
    aple
    -0.76
    ĪĴ
    -0.76
    cor
    -0.75
     Rove
    -0.74
    estial
    -0.74
    auga
    -0.73
    apeake
    -0.73
    POSITIVE LOGITS
     refugee
    1.30
     resettlement
    1.30
     refugees
    1.23
     Refugee
    1.20
     Refugees
    1.16
     asylum
    1.01
     camps
    0.98
     Relief
    0.93
     relief
    0.91
     shelters
    0.90
    Activations Density 0.017%

    No Known Activations