© 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. 3139
    Prev
    Next
    INDEX
    Explanations

    instances of legal terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology and concepts related to court proceedings

    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
    luster
    -0.75
    optim
    -0.72
    ridor
    -0.69
    iasm
    -0.69
    reci
    -0.69
    arya
    -0.68
    imentary
    -0.67
     Dimensions
    -0.67
    lore
    -0.66
    ãĤ´ãĥ³
    -0.65
    POSITIVE LOGITS
     defendants
    1.62
     defendant
    1.56
     Defendants
    1.39
     perjury
    1.38
     Defendant
    1.38
     unconstitutional
    1.35
     convicted
    1.34
     prosecutions
    1.33
     rapists
    1.33
     rapist
    1.32
    Activations Density 0.600%

    No Known Activations