© 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. 4-RES-JB
    11. 7360
    Prev
    Next
    INDEX
    Explanations

    legal and judicial terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and references related to court proceedings and decisions

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

    No Comments

    Negative Logits
     highs
    -0.73
     gigs
    -0.71
     sweets
    -0.64
     nerds
    -0.63
     mushrooms
    -0.62
    ranean
    -0.62
     roaring
    -0.62
     pulses
    -0.61
     Beans
    -0.61
     flares
    -0.59
    POSITIVE LOGITS
     lawful
    1.11
     Plaintiff
    1.07
     Plaint
    1.02
     unlawful
    1.00
     affirmative
    0.99
     petitioner
    0.98
     plaintiff
    0.98
     unlawfully
    0.97
     appellant
    0.96
     Defendant
    0.96
    Activations Density 2.492%

    No Known Activations