© 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. 6-RES-JB
    11. 13663
    Prev
    Next
    INDEX
    Explanations

    specific entities or concepts referred to with the word "RULES"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulations and standards

    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
    du
    -0.70
    athan
    -0.69
    issance
    -0.66
    pocket
    -0.66
    itzer
    -0.65
     Insight
    -0.64
    asca
    -0.63
    aucuses
    -0.63
    oÄŁan
    -0.62
     previews
    -0.62
    POSITIVE LOGITS
     forbids
    1.02
     limits
    0.99
     governs
    0.96
     stip
    0.94
     dictates
    0.93
     strict
    0.92
     enforced
    0.90
     stricter
    0.86
     Limits
    0.86
     governing
    0.86
    Activations Density 0.639%

    No Known Activations