Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16965
    Prev
    Next
    INDEX
    Explanations

    words related to conflict and war, specifically within the context of Syria

    oai_token-act-pair · gpt-3.5-turbo

    references to conflicts and wars, particularly civil wars

    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
    Consumer
    -0.85
     Edison
    -0.80
    uckland
    -0.77
     Patent
    -0.75
     Mercury
    -0.75
    Chance
    -0.75
     patents
    -0.74
     patent
    -0.72
     Whale
    -0.69
     Consumer
    -0.69
    POSITIVE LOGITS
     rebels
    1.22
     insurgents
    1.21
     militias
    1.20
     rebel
    1.12
     insurgency
    1.11
     insurgent
    1.07
     militants
    1.03
     fighters
    1.02
     militia
    1.01
     ceasefire
    1.00
    Activations Density 0.336%

    No Known Activations