© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 2647
    Prev
    Next
    INDEX
    Explanations

    legal terms and definitions related to law and crime

    oai_token-act-pair · gpt-3.5-turbo

    references to legal definitions and consequences related to violence and individual rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -0.78
    soDeliveryDate
    -0.75
     vets
    -0.75
     Tough
    -0.72
     Quartz
    -0.70
     Tracker
    -0.70
     Lilith
    -0.69
     Tuc
    -0.68
     Roose
    -0.68
     Lerner
    -0.68
    POSITIVE LOGITS
     unlawfully
    1.18
     materially
    1.08
     lawful
    1.02
     lawfully
    1.02
     hereby
    1.01
     persons
    1.01
     thereof
    0.98
     unlawful
    0.98
     prohibited
    0.95
     practicable
    0.94
    Activations Density 1.348%

    No Known Activations