© 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. 11-RES-JB
    11. 2360
    Prev
    Next
    INDEX
    Explanations

    mentions of specific countries and political actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of countries and their actions or claims

    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
    aucus
    -0.90
     Bronx
    -0.76
    ascript
    -0.73
     Died
    -0.70
    alach
    -0.68
     gospel
    -0.68
     Valhalla
    -0.67
    IFE
    -0.67
     Caucus
    -0.66
    ãĤ©
    -0.66
    POSITIVE LOGITS
     extrad
    1.19
     invaded
    1.14
     stockp
    1.12
     annexed
    1.12
     retali
    1.07
     warships
    1.04
     retaliate
    1.04
     veto
    1.04
     unilaterally
    1.04
     medd
    1.03
    Activations Density 0.253%

    No Known Activations