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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 22137
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict and military activities in a specific geographical region

    oai_token-act-pair · gpt-3.5-turbo

    references to military conflict and geopolitical tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mecca
    -0.96
     Hayward
    -0.92
     Jinn
    -0.91
     Barker
    -0.89
    Harris
    -0.88
     GHC
    -0.88
    Houston
    -0.87
     scient
    -0.86
     Dawkins
    -0.86
     Carbuncle
    -0.84
    POSITIVE LOGITS
     Ukrainian
    2.26
     Ukrainians
    2.19
     Kiev
    2.17
     Ukraine
    2.14
     Donetsk
    2.14
    Ukraine
    2.12
     Ukrain
    1.95
     Yanukovych
    1.89
     Crimea
    1.84
    Uk
    1.83
    Activations Density 0.281%

    No Known Activations