© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    mentions of casualties and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to fatalities and casualties in conflict situations

    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
    AppData
    -0.78
    enn
    -0.73
    Truth
    -0.70
    CLASSIFIED
    -0.70
    ENN
    -0.67
    innie
    -0.66
    username
    -0.66
    ativity
    -0.64
    Favorite
    -0.64
    ITY
    -0.64
    POSITIVE LOGITS
     clashes
    1.30
     accidents
    1.18
     collisions
    1.18
     gunfire
    1.11
     shootings
    1.09
     explosions
    1.06
     shelling
    1.05
     crashes
    1.03
     airstrikes
    1.01
     bombings
    1.00
    Activations Density 0.151%

    No Known Activations