© 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. 10-RES-JB
    11. 11599
    Prev
    Next
    INDEX
    Explanations

    words related to legal and crime activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of legal terminology or references to laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favorably
    -1.11
     favor
    -1.08
     favoring
    -0.98
     subsidized
    -0.96
     favored
    -0.95
     favors
    -0.92
     flavor
    -0.90
     willfully
    -0.89
     mustache
    -0.88
     categorized
    -0.87
    POSITIVE LOGITS
    Scroll
    1.78
    BBC
    1.72
    Labour
    1.70
    Shape
    1.68
    Scotland
    1.67
    However
    1.64
    Speaking
    1.64
    Writing
    1.60
    Professor
    1.59
    Mr
    1.59
    Activations Density 0.292%

    No Known Activations