© 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. 18546
    Prev
    Next
    INDEX
    Explanations

    legal terms and actions related to challenging or reversing decisions and rulings

    oai_token-act-pair · gpt-3.5-turbo

    instances of legal or judicial actions related to appeals and overturning decisions

    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
    »Ĵ
    -0.85
    ngth
    -0.82
    achine
    -0.78
    anguages
    -0.71
    forums
    -0.71
    ettes
    -0.69
    hov
    -0.68
     cov
    -0.68
     toget
    -0.68
    anguage
    -0.67
    POSITIVE LOGITS
     convictions
    1.19
     rulings
    1.14
     conviction
    1.11
     decision
    1.09
     verdict
    1.08
     injunction
    1.02
     judgment
    1.01
     ruling
    1.00
     decisions
    1.00
     bans
    0.98
    Activations Density 0.187%

    No Known Activations