© 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. 3-RES-JB
    11. 412
    Prev
    Next
    INDEX
    Explanations

    examples of situations or events that provoke strong feelings of anger or shock in the community

    oai_token-act-pair · gpt-3.5-turbo

    expressions of outrage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 3 - anger

    No Comments

    Negative Logits
     Solitaire
    -0.73
    ramer
    -0.73
    uchin
    -0.72
    arnaev
    -0.70
    ramid
    -0.68
    stood
    -0.68
    sembly
    -0.67
    wagen
    -0.66
     livest
    -0.64
    essions
    -0.63
    POSITIVE LOGITS
    ously
    1.17
     indignation
    1.01
    iously
    0.92
     uproar
    0.88
     outrage
    0.85
    ingly
    0.78
    storms
    0.77
     outcry
    0.75
    urous
    0.74
    uously
    0.73
    Activations Density 0.016%

    No Known Activations