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. 8-RES-JB
    6. 21519
    Prev
    Next
    INDEX
    Explanations

    words related to intense anger or fury

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rage" and related emotions or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 8 - anger

    No Comments

    Negative Logits
    icut
    -0.84
    izabeth
    -0.70
    ipment
    -0.69
     Tanz
    -0.69
    ulty
    -0.68
    icals
    -0.67
    Person
    -0.66
     Wonders
    -0.66
    iment
    -0.65
     snug
    -0.64
    POSITIVE LOGITS
    quit
    1.14
    ous
    1.08
    ously
    0.94
    FUL
    0.88
    ful
    0.87
    bol
    0.84
    OUS
    0.84
    acing
    0.75
    ocity
    0.74
    birds
    0.73
    Activations Density 0.076%

    No Known Activations