© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14151
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases and documents

    oai_token-act-pair · gpt-3.5-turbo

    elements related to legal situations or trials

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    urches
    -0.69
     empires
    -0.61
    doms
    -0.56
     wallets
    -0.55
     settlements
    -0.55
     populations
    -0.54
    oris
    -0.54
     Locations
    -0.53
    licts
    -0.53
     economies
    -0.53
    POSITIVE LOGITS
     himself
    1.02
     herself
    0.80
     earlier
    0.79
     hers
    0.74
     hadn
    0.72
     beforehand
    0.71
    ļéĨĴ
    0.70
     unsuccessfully
    0.70
     Himself
    0.67
     anyway
    0.67
    Activations Density 1.181%

    No Known Activations