© 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. 11217
    Prev
    Next
    INDEX
    Explanations

    phrases indicating delegation or decision-making authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to responsibility or decision-making

    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
    hello
    -0.87
    ãĤ¤ãĥĪ
    -0.86
    ãĥĥãĥĪ
    -0.80
    ä¹ĭ
    -0.80
    ãĥŃ
    -0.78
    iazep
    -0.78
    女
    -0.78
    isky
    -0.77
    artifacts
    -0.76
    rets
    -0.73
    POSITIVE LOGITS
     whoever
    1.10
     Congress
    0.99
     discretion
    0.99
     individual
    0.92
     shoulders
    0.92
     us
    0.91
     policymakers
    0.89
     professionals
    0.89
     municipalities
    0.87
     bureaucrats
    0.86
    Activations Density 0.176%

    No Known Activations