© 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. 2-RES-JB
    11. 19729
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and authority

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "govern" and its variations

    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
    uni
    -0.68
    Vs
    -0.67
    chest
    -0.65
     Strike
    -0.62
     Dillon
    -0.61
    Du
    -0.60
    Veter
    -0.60
    Bron
    -0.59
     Colt
    -0.59
    ogh
    -0.59
    POSITIVE LOGITS
     govern
    1.06
     governed
    0.99
    govern
    0.90
     governing
    0.90
    orship
    0.89
     governs
    0.83
    SPONSORED
    0.81
     impart
    0.79
    manship
    0.77
    orial
    0.75
    Activations Density 0.008%

    No Known Activations