Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 12089
    Prev
    Next
    INDEX
    Explanations

    terms related to diplomatic relations and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to diplomatic concepts and relationships

    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
    Interstitial
    -0.83
    nings
    -0.77
    amaz
    -0.76
    runs
    -0.72
    loop
    -0.69
     Alto
    -0.68
    corn
    -0.66
    ravis
    -0.66
    alach
    -0.66
    omial
    -0.65
    POSITIVE LOGITS
     corps
    1.03
    plom
    0.99
     diplomatic
    0.99
     diplomacy
    0.97
     diplomats
    0.91
     embassy
    0.90
     deleg
    0.90
     embassies
    0.89
     envoy
    0.87
     droid
    0.82
    Activations Density 0.033%

    No Known Activations