© 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. 8-RES-JB
    11. 7823
    Prev
    Next
    INDEX
    Explanations

    terms related to compliance with rules and regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compliance and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    landers
    -0.69
    iller
    -0.68
    retty
    -0.66
    mAh
    -0.65
    laugh
    -0.64
    mu
    -0.63
    john
    -0.62
    chat
    -0.62
    ulz
    -0.62
    br
    -0.61
    POSITIVE LOGITS
     orders
    1.11
     laws
    1.05
     regulations
    1.04
     mandates
    1.00
     directives
    0.99
     strict
    0.99
     rules
    0.98
     requirements
    0.96
     agreements
    0.96
     norms
    0.96
    Activations Density 0.155%

    No Known Activations