© 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. 3-RES-JB
    11. 12841
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and judicial proceedings

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and discussions related to court cases and judicial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĺ
    -0.74
     FANTASY
    -0.71
     Paradox
    -0.71
     realise
    -0.70
    enment
    -0.70
    oubted
    -0.69
     rejoice
    -0.68
    inav
    -0.68
    apore
    -0.67
     âĨ
    -0.67
    POSITIVE LOGITS
     unconstitutional
    0.85
     legally
    0.84
     illegally
    0.80
     vetting
    0.80
     constitutionally
    0.77
     statewide
    0.77
     ineligible
    0.77
     federally
    0.76
     subpoen
    0.76
     misdemeanor
    0.76
    Activations Density 2.845%

    No Known Activations