© 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. 4-RES-JB
    11. 15587
    Prev
    Next
    INDEX
    Explanations

    terms related to combat and battle, particularly involving actions against enemies

    oai_token-act-pair · gpt-3.5-turbo

    references to enemies and combat in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aughs
    -0.80
    cipled
    -0.77
    docs
    -0.76
    ilege
    -0.74
    ories
    -0.73
    dated
    -0.71
    yss
    -0.70
    Anth
    -0.69
    cially
    -0.69
    xit
    -0.69
    POSITIVE LOGITS
     respawn
    0.85
     combatants
    0.81
     enemy
    0.81
     enemies
    0.81
     NPCs
    0.76
     Ceres
    0.76
     encountered
    0.74
     roam
    0.74
     HUD
    0.74
     invade
    0.73
    Activations Density 0.048%

    No Known Activations