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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2546
    Prev
    Next
    INDEX
    Explanations

    mentions of humanitarian crises and aid efforts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of humanitarian issues and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.89
    rams
    -0.84
    creen
    -0.84
    âĸ¬
    -0.81
    ription
    -0.80
    acular
    -0.79
    arnaev
    -0.77
    auri
    -0.74
    eters
    -0.72
    essor
    -0.72
    POSITIVE LOGITS
     aid
    1.00
     humanitarian
    1.00
     crises
    0.94
     Aid
    0.91
     refugees
    0.91
     intervention
    0.91
     assistance
    0.89
     organizations
    0.89
     crisis
    0.88
     organisations
    0.87
    Activations Density 0.032%

    No Known Activations