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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11972
    Prev
    Next
    INDEX
    Explanations

    legal terms and court-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology and references to court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.72
    Enlarge
    -0.68
     Toast
    -0.66
    omething
    -0.66
    abouts
    -0.65
    Yep
    -0.64
     booze
    -0.64
     roaring
    -0.64
     Bounce
    -0.63
    worldly
    -0.63
    POSITIVE LOGITS
     therefore
    1.40
     furthermore
    1.34
     contends
    1.27
     concludes
    1.27
     stated
    1.26
     concluded
    1.26
     emphasized
    1.23
     recommends
    1.21
     asserts
    1.21
     additionally
    1.19
    Activations Density 0.466%

    No Known Activations