© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 2389
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts, focusing particularly on mentions of the word "law."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "law"

    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
     Dak
    -0.78
     Flavoring
    -0.73
     Crescent
    -0.73
     Scion
    -0.73
    vae
    -0.72
     Mul
    -0.72
    emonic
    -0.67
    ched
    -0.66
     Rubber
    -0.66
     Pixie
    -0.63
    POSITIVE LOGITS
     enforcement
    1.35
     Enforcement
    1.05
    enforcement
    1.05
    lessness
    1.05
     law
    0.97
     abiding
    0.97
    suit
    0.96
     lawy
    0.94
    suits
    0.94
    breakers
    0.87
    Activations Density 0.037%

    No Known Activations