© 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. 10-RES-JB
    11. 16684
    Prev
    Next
    INDEX
    Explanations

    references to legal or governmental powers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 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 @ 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
     Mour
    -0.66
     Soda
    -0.65
    gaard
    -0.65
    ModLoader
    -0.64
     Resist
    -0.63
     Lonely
    -0.62
    algia
    -0.61
    eros
    -0.61
     flyers
    -0.60
     Cron
    -0.60
    POSITIVE LOGITS
     delegated
    1.43
     conferred
    1.26
     granted
    1.22
     vested
    1.21
     powers
    1.15
     Powers
    0.96
     discretion
    0.95
     constitutionally
    0.93
     authorizing
    0.93
     afforded
    0.91
    Activations Density 0.073%

    No Known Activations