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. 3-RES-JB
    6. 13753
    Prev
    Next
    INDEX
    Explanations

    references to NATO activities and relationships in global politics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and mentions of NATO

    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
    âĸ¬
    -0.83
    ,,,,,,,,
    -0.75
    nit
    -0.72
    lights
    -0.72
    Wheel
    -0.72
    sbm
    -0.71
    iple
    -0.69
    light
    -0.69
    à
    -0.69
    market
    -0.68
    POSITIVE LOGITS
     annex
    0.91
     NATO
    0.91
     Allies
    0.89
     Nato
    0.86
     treaty
    0.84
     enlarg
    0.83
    ndum
    0.82
     allies
    0.80
     ally
    0.78
    istani
    0.76
    Activations Density 0.009%

    No Known Activations