© 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. 8-RES-JB
    11. 3171
    Prev
    Next
    INDEX
    Explanations

    international relations-related terms and statements

    oai_token-act-pair · gpt-3.5-turbo

    references to comments and statements about political or diplomatic matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Craigslist
    -0.93
     foreclosure
    -0.91
     Creep
    -0.87
     Lovecraft
    -0.79
     tornado
    -0.79
     Avery
    -0.78
     Bigfoot
    -0.76
    atown
    -0.75
     Bronx
    -0.75
     Arkham
    -0.74
    POSITIVE LOGITS
    plom
    1.19
     Lavrov
    1.18
     diplomatic
    1.16
     diplomats
    1.14
     diplomacy
    1.09
    oglu
    1.05
     Nato
    1.04
     Jinping
    1.04
    inational
    1.04
     envoy
    1.02
    Activations Density 0.961%

    No Known Activations