© 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. 11703
    Prev
    Next
    INDEX
    Explanations

    legal terms and court-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to judicial rulings and legal decisions

    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
    perture
    -0.78
     Plot
    -0.67
     weap
    -0.66
    Plot
    -0.64
     Growth
    -0.64
    ope
    -0.63
     Volunteers
    -0.62
    ohyd
    -0.60
    asus
    -0.60
     liaison
    -0.59
    POSITIVE LOGITS
     upholding
    1.53
     legalizing
    1.32
     overturn
    1.28
     denying
    1.13
     dismissing
    1.12
     upheld
    1.08
     reversing
    1.07
     rejecting
    1.06
     granting
    1.05
     awarding
    1.03
    Activations Density 0.099%

    No Known Activations