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. 19086
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "is being" is used in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ongoing actions or states described by the word "being."

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Relief
    -0.76
     Mobility
    -0.72
     Elements
    -0.68
    PsyNetMessage
    -0.68
     Gord
    -0.67
     Lag
    -0.66
     srfAttach
    -0.66
     Taxes
    -0.62
     Wid
    -0.62
     Sop
    -0.62
    POSITIVE LOGITS
     replaced
    1.00
     evaluated
    0.96
     hailed
    0.95
     investigated
    0.95
     phased
    0.92
     chased
    0.90
     pursued
    0.89
     attacked
    0.88
     assessed
    0.88
     tested
    0.88
    Activations Density 0.068%

    No Known Activations