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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2850
    Prev
    Next
    INDEX
    Explanations

    unwritten rules or societal norms

    oai_token-act-pair · gpt-3.5-turbo

    references to unwritten social rules and norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orescence
    -0.83
    iris
    -0.76
    inventoryQuantity
    -0.74
    alyst
    -0.73
    urch
    -0.72
    irit
    -0.71
    trak
    -0.70
    vas
    -0.69
    ONSORED
    -0.68
    jet
    -0.67
    POSITIVE LOGITS
     rules
    2.06
    rules
    1.94
     Rules
    1.78
     rule
    1.77
    iquette
    1.75
    Rule
    1.75
     guidelines
    1.67
     etiquette
    1.66
    Rules
    1.64
     Rule
    1.58
    Activations Density 0.646%

    No Known Activations