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. 8-RES-JB
    6. 16485
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent clashes or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to clashes or conflicts between groups, particularly involving protests or riots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     immortality
    -0.94
    ģĸ
    -0.90
    perfect
    -0.81
    ãĤ´ãĥ³
    -0.80
    Perfect
    -0.75
     trillions
    -0.73
    nesia
    -0.72
     Lifetime
    -0.72
    arenthood
    -0.70
    vana
    -0.70
    POSITIVE LOGITS
     demonstrators
    1.32
     protesters
    1.31
     protestors
    1.24
     gunmen
    1.21
     assailants
    1.19
     Protesters
    1.10
     riot
    1.09
     clashes
    1.09
     chanting
    1.08
     attackers
    1.07
    Activations Density 0.448%

    No Known Activations