© 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. 11-RES-JB
    11. 15031
    Prev
    Next
    INDEX
    Explanations

    violations of laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal statutes and violations related to laws and constitutional issues

    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
    apest
    -0.70
     Likes
    -0.63
    Pie
    -0.63
    rowth
    -0.61
    iban
    -0.59
    anmar
    -0.58
    BuyableInstoreAndOnline
    -0.58
    aden
    -0.57
    rise
    -0.57
    adjust
    -0.56
    POSITIVE LOGITS
     prohibiting
    1.05
     prohibitions
    1.00
     obligations
    0.98
     laws
    0.95
     norms
    0.93
    laws
    0.88
     rules
    0.88
     by
    0.86
     governing
    0.85
     deadlines
    0.84
    Activations Density 0.195%

    No Known Activations