© 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. 9-RES-JB
    11. 17823
    Prev
    Next
    INDEX
    Explanations

    mentions related to military or political actions involving the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States and its actions regarding military strategies and interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bred
    -0.76
    bm
    -0.71
     Parables
    -0.68
     Chatt
    -0.66
    idated
    -0.66
    venue
    -0.64
     srfAttach
    -0.64
    emetery
    -0.63
     Synd
    -0.63
     Babe
    -0.63
    POSITIVE LOGITS
     embassy
    1.07
     Embassy
    1.02
     diplomats
    0.99
     envoy
    0.94
     neocons
    0.92
     diplomat
    0.90
     ambassador
    0.88
     diplomatic
    0.88
     airstrikes
    0.87
     ally
    0.87
    Activations Density 0.211%

    No Known Activations