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. 3-RES-JB
    6. 22457
    Prev
    Next
    INDEX
    Explanations

    phrases related to yelling or shouting

    oai_token-act-pair · gpt-3.5-turbo

    instances of shouting or yelling

    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
    Not in Any Lists

    No Comments

    Negative Logits
    uncture
    -0.79
    nesota
    -0.76
    folios
    -0.75
    uton
    -0.72
    algia
    -0.72
    insula
    -0.66
    ________________________________
    -0.66
    inion
    -0.66
    folio
    -0.65
    flix
    -0.65
    POSITIVE LOGITS
     louder
    1.11
     loudly
    0.99
     shout
    0.94
     shouted
    0.91
     aloud
    0.90
     shouts
    0.87
     shouting
    0.86
     yelled
    0.85
     yells
    0.85
     slogans
    0.81
    Activations Density 0.022%

    No Known Activations