© 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 EvalsExportsAPI 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. 3-RES-JB
    11. 24488
    Prev
    Next
    INDEX
    Explanations

    mentions of Egyptian political figure, Hosni Mubarak

    oai_token-act-pair · gpt-3.5-turbo

    references to the former Egyptian President Hosni Mubarak

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shapeshifter
    -0.79
     Samoa
    -0.76
    $$$$
    -0.75
     Scotia
    -0.72
     Volks
    -0.71
     Lauder
    -0.70
     Wonderland
    -0.70
    âĢ¢âĢ¢
    -0.68
     Hurricanes
    -0.65
     Geographic
    -0.65
    POSITIVE LOGITS
    sein
    1.05
    kins
    1.02
    iery
    1.02
    kinson
    1.01
    nian
    0.94
    eni
    0.93
     Hos
    0.92
    ni
    0.90
    oslav
    0.89
    oly
    0.89
    Activations Density 0.008%

    No Known Activations