© 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. 0-RES-JB
    11. 15745
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of legal justice

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ules
    -0.70
     TABLE
    -0.70
    ergic
    -0.67
    addon
    -0.65
    bus
    -0.65
     bump
    -0.64
    azines
    -0.62
    nas
    -0.62
    bs
    -0.62
    Chat
    -0.61
    POSITIVE LOGITS
     justice
    4.13
    justice
    2.86
    Justice
    2.47
     Justice
    2.38
     injustice
    1.95
     JUSTICE
    1.93
     fairness
    1.43
     justices
    1.40
     judicial
    1.31
     righteousness
    1.31
    Activations Density 0.015%

    No Known Activations