© 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. 16680
    Prev
    Next
    INDEX
    Explanations

    mentions of specific countries related to military or political actions

    oai_token-act-pair · gpt-3.5-turbo

    references to military intervention in Syria and related conflicts

    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
    haw
    -0.83
     Wim
    -0.82
    atin
    -0.74
     Aberdeen
    -0.73
    bery
    -0.70
    Wilson
    -0.69
     Greenwich
    -0.69
     newcom
    -0.68
    Companies
    -0.68
     Cologne
    -0.67
    POSITIVE LOGITS
     ravaged
    0.93
     flared
    0.85
     unilaterally
    0.80
     illegally
    0.77
     escalated
    0.75
     contingency
    0.74
     invaded
    0.74
     rubble
    0.73
     crisis
    0.73
     conflict
    0.73
    Activations Density 0.132%

    No Known Activations