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. 0-RES-JB
    6. 10738
    Prev
    Next
    INDEX
    Explanations

    instances of words related to the concept of 'occurring'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "occurring."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ada
    -0.63
    bag
    -0.62
    issors
    -0.61
    rets
    -0.58
     mock
    -0.58
     rethink
    -0.57
     Pictures
    -0.57
    LI
    -0.56
     digs
    -0.56
    LO
    -0.56
    POSITIVE LOGITS
     occurring
    3.45
     happening
    1.54
     arising
    1.45
     occurrence
    1.45
     occurs
    1.43
     occ
    1.43
     occur
    1.42
     appearing
    1.37
     occurred
    1.31
     originating
    1.29
    Activations Density 0.010%

    No Known Activations