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

    Neuronpedia

    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. 4-RES-JB
    11. 17069
    Prev
    Next
    INDEX
    Explanations

    mentions of the NATO organization

    oai_token-act-pair · gpt-3.5-turbo

    mentions of NATO and its related contexts

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

    No Comments

    Negative Logits
    lights
    -0.80
    nit
    -0.79
    iple
    -0.76
    market
    -0.73
    sbm
    -0.72
    light
    -0.71
    hot
    -0.70
     Tsu
    -0.70
    ,,,,,,,,
    -0.69
    thritis
    -0.69
    POSITIVE LOGITS
     Allies
    0.94
     NATO
    0.86
    ndum
    0.85
     annex
    0.83
     treaty
    0.81
    wana
    0.76
     enlarg
    0.76
     Treaty
    0.74
     allies
    0.73
     expansion
    0.72
    Activations Density 0.012%

    No Known Activations