© 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. 20492
    Prev
    Next
    INDEX
    Explanations

    instances of the word "authority" within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to authority and its various contexts

    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
    wagen
    -0.78
    hire
    -0.76
    akeru
    -0.72
    neys
    -0.72
    enegger
    -0.71
    kies
    -0.70
    hematic
    -0.68
    reens
    -0.68
    bart
    -0.68
    orno
    -0.67
    POSITIVE LOGITS
     delegated
    1.13
     vested
    1.11
     authority
    1.10
     overseeing
    0.91
     conferred
    0.87
     exercised
    0.86
     figures
    0.85
     authorizing
    0.82
     granted
    0.81
    alties
    0.79
    Activations Density 0.037%

    No Known Activations