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

    Neuronpedia

    APICircuit 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. 13745
    Prev
    Next
    INDEX
    Explanations

    phrases related to intense anger or fury

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rage" in various contexts

    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
    icut
    -0.80
    lder
    -0.74
     Donation
    -0.74
    missions
    -0.72
    uchin
    -0.70
    ramer
    -0.70
    ipment
    -0.69
    iden
    -0.68
     Liberties
    -0.68
    rica
    -0.67
    POSITIVE LOGITS
     rage
    1.32
     fury
    1.07
     indignation
    0.97
    quit
    0.95
     raging
    0.91
     anger
    0.85
     furnace
    0.84
     outburst
    0.82
     wrath
    0.80
     raged
    0.79
    Activations Density 0.009%

    No Known Activations