© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15292
    Prev
    Next
    INDEX
    Explanations

    mentions of international organizations, specifically NATO

    oai_token-act-pair · gpt-3.5-turbo

    references to NATO and related geopolitical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ega
    -1.01
    lder
    -0.82
     Cash
    -0.77
     Fiesta
    -0.77
     droid
    -0.72
     Bib
    -0.71
     fork
    -0.71
     Milky
    -0.70
     ride
    -0.68
     Guru
    -0.68
    POSITIVE LOGITS
    NAT
    3.40
     NAT
    1.96
     nat
    1.61
    ogan
    1.59
    nat
    1.58
    ALT
    1.00
     Nort
    0.97
    Nat
    0.93
     Ankara
    0.91
    MAP
    0.90
    Activations Density 0.038%

    No Known Activations