© 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 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. 4201
    Prev
    Next
    INDEX
    Explanations

    terms related to foreign policy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of foreign policy

    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
    amaz
    -0.81
    FORMATION
    -0.81
    upon
    -0.79
    oven
    -0.79
    igans
    -0.79
    berry
    -0.74
    DAY
    -0.73
    amination
    -0.72
    username
    -0.72
    unn
    -0.71
    POSITIVE LOGITS
     superpower
    1.01
     advisor
    1.00
     adviser
    1.00
     advisors
    1.00
     advisers
    0.97
     theorist
    0.92
     crises
    0.91
     objectives
    0.90
     diplomacy
    0.88
     correctness
    0.85
    Activations Density 0.058%

    No Known Activations