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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 10403
    Prev
    Next
    INDEX
    Explanations

    words related to emotions of anger

    oai_token-act-pair · gpt-3.5-turbo

    references to anger or expressions of anger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 1 - anger

    No Comments

    Negative Logits
    pmwiki
    -0.94
    sites
    -0.90
    arent
    -0.80
    ovember
    -0.76
    ppa
    -0.75
    issue
    -0.74
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.74
    anship
    -0.74
    Vert
    -0.73
    itals
    -0.72
    POSITIVE LOGITS
     angry
    1.21
     outburst
    0.90
     indignation
    0.88
     anger
    0.86
     fury
    0.85
     shouts
    0.84
     mobs
    0.81
     furious
    0.79
     parting
    0.79
     unhappy
    0.78
    Activations Density 0.013%

    No Known Activations