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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2385
    Prev
    Next
    INDEX
    Explanations

    lawsuits and legal rulings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal rulings and court decisions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Lonely
    -0.87
     TEAM
    -0.74
     flares
    -0.73
     rumours
    -0.73
     gobl
    -0.72
     highs
    -0.71
     tours
    -0.71
    agra
    -0.71
     Hai
    -0.70
     Rune
    -0.70
    POSITIVE LOGITS
     statute
    1.40
     appellant
    1.37
     plaintiffs
    1.36
     plaintiff
    1.36
     unconstitutional
    1.31
     Plaint
    1.30
     constitutional
    1.30
     defendant
    1.30
     constitutionally
    1.25
     appellate
    1.24
    Activations Density 1.001%

    No Known Activations