© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 14422
    Prev
    Next
    INDEX
    Explanations

    terms related to military contexts, warfare, and combat

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "enemy" and related concepts in the context of conflict and combat

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ħ¢
    -0.80
    uesday
    -0.79
    oled
    -0.77
    aus
    -0.77
    otto
    -0.76
    ucket
    -0.75
    orrow
    -0.75
    aza
    -0.74
    ocument
    -0.74
    ajo
    -0.73
    POSITIVE LOGITS
     combatants
    1.06
     Enemy
    0.97
     enemy
    0.94
     foe
    0.83
     takeover
    0.80
    enemy
    0.80
     fighters
    0.79
     soldiers
    0.75
     soldier
    0.74
     invaded
    0.74
    Activations Density 0.026%

    No Known Activations