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. 2-RES-JB
    6. 16614
    Prev
    Next
    INDEX
    Explanations

    phrases related to yelling

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "yell" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folios
    -0.86
    Gaza
    -0.74
    pocket
    -0.73
    uncture
    -0.72
    olitics
    -0.72
    flix
    -0.71
    VICE
    -0.70
     foss
    -0.69
    uton
    -0.68
    tnc
    -0.67
    POSITIVE LOGITS
     louder
    1.00
     yell
    0.96
     yells
    0.95
    ows
    0.85
     chants
    0.84
     yelled
    0.83
     shouts
    0.83
     bark
    0.82
     yelling
    0.81
     shout
    0.78
    Activations Density 0.007%

    No Known Activations