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. 4-RES-JB
    6. 3443
    Prev
    Next
    INDEX
    Explanations

    news articles related to military conflicts and political events

    oai_token-act-pair · gpt-3.5-turbo

    references to casualties and military actions in conflict situations

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

    No Comments

    Negative Logits
     Cary
    -0.70
     Wonderland
    -0.70
     Madness
    -0.66
     Wilde
    -0.66
     Packers
    -0.63
    Runner
    -0.61
    Madison
    -0.60
     Milwaukee
    -0.60
     Garfield
    -0.59
    Ear
    -0.59
    POSITIVE LOGITS
    zbollah
    1.05
     ceasefire
    1.03
     Nato
    1.01
     Hezbollah
    0.95
     Islamist
    0.94
     Rohingya
    0.90
     ISIL
    0.89
     Shiite
    0.87
     Ankara
    0.86
     Daesh
    0.86
    Activations Density 2.004%

    No Known Activations