© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 17861
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions, specifically involving restraining orders or legal silencing

    oai_token-act-pair · gpt-3.5-turbo

    references to gag orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hurricanes
    -0.72
    cession
    -0.63
    undai
    -0.63
     Purg
    -0.63
    xual
    -0.61
     Blessed
    -0.61
    guided
    -0.60
    appropriate
    -0.57
     Parenthood
    -0.57
     Crimson
    -0.56
    POSITIVE LOGITS
    glers
    1.28
     gag
    1.06
     reel
    0.86
    eries
    0.82
    bag
    0.80
    bags
    0.79
     reflex
    0.79
    liest
    0.75
    gers
    0.72
    weed
    0.72
    Activations Density 0.008%

    No Known Activations