© 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. 12-RES-JB
    11. 3286
    Prev
    Next
    INDEX
    Explanations

    information related to conflicts, bombings, and military interventions in Syria

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of violence and conflict-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    Oracle
    -1.02
     Cricket
    -1.01
    uckland
    -0.98
     Honolulu
    -0.89
     cricket
    -0.89
     Oracle
    -0.88
     Rodney
    -0.87
     NX
    -0.86
     Navajo
    -0.86
     Bonds
    -0.85
    POSITIVE LOGITS
     Assad
    2.19
    Assad
    2.07
     Damascus
    2.05
     Syrian
    2.01
     Aleppo
    2.01
    Syria
    1.95
    Syrian
    1.95
     Syria
    1.94
     Syrians
    1.91
     Bashar
    1.91
    Activations Density 0.523%

    No Known Activations