© 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. 1-RES-JB
    11. 10272
    Prev
    Next
    INDEX
    Explanations

    words related to enforcement, especially in law or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to enforcing laws, regulations, or rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Columb
    -0.75
    odor
    -0.69
    hoff
    -0.69
    Pic
    -0.68
     Basil
    -0.67
    ones
    -0.67
     Dak
    -0.67
    asus
    -0.66
     Hydro
    -0.66
    rax
    -0.66
    POSITIVE LOGITS
     enforce
    1.42
     enforced
    1.13
     enforcing
    1.12
     enforcement
    1.05
     compliance
    1.01
     undermin
    0.85
    querque
    0.85
     crackdown
    0.82
     conflic
    0.82
     defe
    0.81
    Activations Density 0.008%

    No Known Activations