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. 11532
    Prev
    Next
    INDEX
    Explanations

    legal action terms like "lawsuit," "complaint," and "petition."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal actions and filings

    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
    oured
    -0.86
    ateurs
    -0.69
    ours
    -0.68
    peak
    -0.67
    oren
    -0.66
     taught
    -0.62
    ored
    -0.61
    oring
    -0.61
     lured
    -0.60
     Palest
    -0.59
    POSITIVE LOGITS
     paperwork
    0.93
     complaint
    0.85
    idav
    0.83
     lawsuit
    0.83
     papers
    0.81
     FIR
    0.81
     arbitration
    0.77
     Correction
    0.72
    rection
    0.71
     muster
    0.71
    Activations Density 0.089%

    No Known Activations