© 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. 11-RES-JB
    6. 7847
    Prev
    Next
    INDEX
    Explanations

    references to legal authority and power

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to governmental authority and legal powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aughtered
    -0.70
    spir
    -0.67
     smugglers
    -0.65
    ndra
    -0.65
    comed
    -0.65
    akeru
    -0.62
    pointers
    -0.61
    gae
    -0.60
    ourney
    -0.59
    bsite
    -0.59
    POSITIVE LOGITS
     authority
    1.58
     discretion
    1.48
     powers
    1.47
     jurisdiction
    1.45
     control
    1.30
     responsibility
    1.28
     power
    1.28
     autonomy
    1.23
     veto
    1.22
     latitude
    1.21
    Activations Density 0.528%

    No Known Activations