© 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. 2742
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Syria or entities related to it

    oai_token-act-pair · gpt-3.5-turbo

    references to the Syrian conflict and related entities

    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
    ersen
    -0.82
    otle
    -0.78
    inarily
    -0.77
    deck
    -0.77
    raviolet
    -0.76
    print
    -0.75
    tops
    -0.73
    ãģĨ
    -0.72
    inburgh
    -0.72
    gow
    -0.69
    POSITIVE LOGITS
     Kurds
    1.16
    Assad
    1.12
     rebels
    1.11
     Homs
    1.08
     Arab
    1.08
     rebel
    1.06
     Assad
    1.05
     Aleppo
    1.02
     Refugees
    1.01
     refugees
    1.01
    Activations Density 0.053%

    No Known Activations