© 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. 20837
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing wars or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to various "wars" on different issues or topics

    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
    NBA
    -0.72
    BIP
    -0.71
    ittal
    -0.71
    Patch
    -0.70
    rete
    -0.68
    HF
    -0.68
    yip
    -0.67
    meet
    -0.67
    UF
    -0.67
    Trigger
    -0.65
    POSITIVE LOGITS
     drugs
    1.23
     Drugs
    1.10
     terror
    1.07
     whistleblowers
    0.97
     terrorism
    0.95
    terror
    0.93
     poverty
    0.89
     Terror
    0.87
     Poverty
    0.82
     Terrorism
    0.79
    Activations Density 0.086%

    No Known Activations