© 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. 11-RES-JB
    11. 20367
    Prev
    Next
    INDEX
    Explanations

    words related to anger and frustration

    oai_token-act-pair · gpt-3.5-turbo

    references to anger and related emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 11 - anger

    No Comments

    Negative Logits
    glas
    -0.70
     livest
    -0.68
     Places
    -0.66
     Bless
    -0.64
     Sound
    -0.64
    nown
    -0.62
     Wonders
    -0.62
    uchin
    -0.62
    foundation
    -0.61
     snug
    -0.58
    POSITIVE LOGITS
    quit
    1.17
    rained
    1.04
     against
    0.91
    ously
    0.88
     indignation
    0.88
    storms
    0.86
     directed
    0.83
     mobs
    0.82
    rage
    0.80
     rage
    0.80
    Activations Density 0.135%

    No Known Activations