© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8805
    Prev
    Next
    INDEX
    Explanations

    mentions of diplomatic actions or efforts in a political context

    oai_token-act-pair · gpt-3.5-turbo

    references to diplomatic relations and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alach
    -0.90
    gger
    -0.80
    isode
    -0.80
    hra
    -0.78
    stadt
    -0.73
    runs
    -0.72
    arching
    -0.71
    stood
    -0.71
    ras
    -0.70
    nings
    -0.70
    POSITIVE LOGITS
     diplomatic
    1.09
     diplomacy
    0.99
     embassy
    0.94
     correctness
    0.92
     espionage
    0.91
     immunity
    0.91
     consulate
    0.89
     diplomats
    0.86
     corps
    0.85
     cables
    0.85
    Activations Density 0.011%

    No Known Activations