© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 7838
    Prev
    Next
    INDEX
    Explanations

    names of political leaders, particularly presidents

    oai_token-act-pair · gpt-3.5-turbo

    references to various Presidents, particularly Vladimir Putin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckland
    -0.75
    wich
    -0.68
    kinson
    -0.67
    nesota
    -0.66
    é¾
    -0.65
    halla
    -0.65
     multiplier
    -0.64
    essen
    -0.62
     Osc
    -0.61
    atown
    -0.60
    POSITIVE LOGITS
     Bashar
    0.90
     Recep
    0.80
     Vladimir
    0.80
     Edu
    0.79
     Sergio
    0.78
     Boris
    0.75
     Barack
    0.75
     Leon
    0.75
     Francois
    0.74
     Sheikh
    0.74
    Activations Density 0.080%

    No Known Activations