Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 1200
    Prev
    Next
    INDEX
    Explanations

    words related to legal procedures like swearing oaths or making statements under oath

    oai_token-act-pair · gpt-3.5-turbo

    references to oaths or swearing in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Stage
    -0.72
     guiActiveUnfocused
    -0.71
    markets
    -0.70
    ATA
    -0.70
    Mind
    -0.69
     Closed
    -0.68
    actionDate
    -0.67
    iga
    -0.67
     Shutterstock
    -0.65
     Stras
    -0.65
    POSITIVE LOGITS
     oath
    1.51
     sworn
    1.25
     swearing
    1.16
     swear
    1.09
     swore
    1.03
     vow
    0.97
     allegiance
    0.91
     Oath
    0.90
    kowski
    0.79
    thouse
    0.73
    Activations Density 0.028%

    No Known Activations