© 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. 20790
    Prev
    Next
    INDEX
    Explanations

    terms related to war, combat, and conflict

    oai_token-act-pair · gpt-3.5-turbo

    historical references related to war

    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
    ethyst
    -0.93
    Ell
    -0.89
     fingerprint
    -0.86
    Magikarp
    -0.83
    plex
    -0.80
     Grassley
    -0.78
    HOU
    -0.77
    perm
    -0.76
    PIN
    -0.75
     Deposit
    -0.74
    POSITIVE LOGITS
     war
    2.13
     War
    2.10
    War
    1.99
     warfare
    1.88
     wars
    1.88
    war
    1.84
     combatants
    1.75
     Warfare
    1.74
     Wars
    1.71
     WAR
    1.68
    Activations Density 0.384%

    No Known Activations