© 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. 11-RES-JB
    11. 2236
    Prev
    Next
    INDEX
    Explanations

    words related to conflicts, specifically civil wars

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing conflicts and wars

    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
    umbn
    -0.71
    bnb
    -0.70
     infinity
    -0.68
    ECD
    -0.66
    Chance
    -0.65
    asonic
    -0.62
     Transactions
    -0.62
     Tennis
    -0.62
     Gifts
    -0.61
    MET
    -0.60
    POSITIVE LOGITS
     raged
    1.17
     raging
    1.16
    torn
    1.12
    lords
    1.04
     ravaged
    0.99
     flared
    0.97
     erupted
    0.96
    lord
    0.94
     engulf
    0.93
     plag
    0.90
    Activations Density 0.117%

    No Known Activations