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

    Neuronpedia

    Jacobian LensNEW
    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. 24133
    Prev
    Next
    INDEX
    Explanations

    references to the emotion of anger

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "anger" and related expressions of frustration or dissatisfaction

    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
    ©¶æ¥µ
    -0.95
    ©¶æ
    -0.94
    estinal
    -0.88
    İĭ
    -0.86
    abeth
    -0.78
    eah
    -0.77
    prus
    -0.74
    ichick
    -0.74
     Janeiro
    -0.74
    ij
    -0.72
    POSITIVE LOGITS
    ously
    1.00
    ous
    0.91
    anger
    0.85
    OUS
    0.77
    ishly
    0.74
    xual
    0.72
    angers
    0.70
    gers
    0.67
    bang
    0.67
     Jinn
    0.66
    Activations Density 0.013%

    No Known Activations