Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4194
    Prev
    Next
    INDEX
    Explanations

    words related to emotions like anger and frustration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "anger" and related expressions

    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
    ©¶æ
    -0.85
    İĭ
    -0.75
     approximate
    -0.69
    margin
    -0.66
     periodic
    -0.65
     Scal
    -0.64
    itions
    -0.63
    eah
    -0.62
     evenly
    -0.62
    SOURCE
    -0.60
    POSITIVE LOGITS
    anger
    1.28
    angers
    0.93
    rage
    0.79
    bang
    0.78
    fire
    0.76
    azi
    0.75
    ously
    0.74
    ous
    0.73
    xual
    0.72
    enment
    0.69
    Activations Density 0.005%

    No Known Activations