© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2310
    Prev
    Next
    INDEX
    Explanations

    international political conflicts and diplomatic relationships

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to geopolitical entities and their actions in international relations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    tnc
    -0.79
    EStream
    -0.78
    Translation
    -0.77
    ĺħ
    -0.74
    akings
    -0.73
    %%%%
    -0.71
    «ĺ
    -0.70
    NetMessage
    -0.69
    Interstitial
    -0.69
    RIP
    -0.67
    POSITIVE LOGITS
     denies
    1.43
     accuses
    1.23
     contends
    1.19
     opposes
    1.18
     maintains
    1.16
     disagrees
    1.15
     insists
    1.14
     has
    1.13
     argues
    1.13
     denied
    1.11
    Activations Density 0.359%

    No Known Activations