© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 7457
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or societal conflicts or initiatives, such as "war on drugs" or "war on terror."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention various "wars" or conflicts in a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RECT
    -0.77
    gaard
    -0.76
    rete
    -0.76
    nces
    -0.73
    SourceFile
    -0.73
    iate
    -0.71
    auga
    -0.66
    çīĪ
    -0.66
    VP
    -0.66
    comings
    -0.65
    POSITIVE LOGITS
     opioids
    0.73
     Drugs
    0.73
     terrorism
    0.72
     terror
    0.71
     Armageddon
    0.69
     Iraq
    0.69
     distraction
    0.67
     Atlantis
    0.67
     modernization
    0.67
     socialism
    0.66
    Activations Density 0.080%

    No Known Activations