© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 18019
    Prev
    Next
    INDEX
    Explanations

    phrases related to international politics and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating accusations and diplomatic relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itud
    -0.86
    emetery
    -0.82
    dra
    -0.81
    alach
    -0.80
     glim
    -0.79
    ando
    -0.76
    aucus
    -0.74
    ãĤ©
    -0.73
    ascript
    -0.73
    mble
    -0.72
    POSITIVE LOGITS
     Nato
    1.29
     UNESCO
    1.27
     NATO
    1.25
     Crimea
    1.12
     foreigners
    1.09
     international
    1.08
     WTO
    1.08
     diplomatic
    1.07
     Western
    1.03
     Lavrov
    1.03
    Activations Density 0.526%

    No Known Activations