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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 22584
    Prev
    Next
    INDEX
    Explanations

    countries and regions associated with conflict and military presence

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries involved in military conflicts and the associated geopolitical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antioxid
    -0.84
    uristic
    -0.72
     Draper
    -0.68
     aroma
    -0.68
     tast
    -0.65
    neau
    -0.65
    iously
    -0.65
     warranties
    -0.65
     listener
    -0.65
    letcher
    -0.64
    POSITIVE LOGITS
     ravaged
    1.03
     Libya
    1.00
     Hezbollah
    1.00
     Syria
    0.96
    Syria
    0.94
     Iraq
    0.94
    istan
    0.93
     Afghanistan
    0.92
    oglu
    0.90
    abad
    0.90
    Activations Density 0.537%

    No Known Activations