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. 4-RES-JB
    6. 19213
    Prev
    Next
    INDEX
    Explanations

    phrases related to bankruptcy

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bankruptcy."

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

    No Comments

    Negative Logits
    eele
    -0.92
    eq
    -0.84
    alle
    -0.74
    resso
    -0.73
    nesota
    -0.72
    population
    -0.71
    enough
    -0.71
    Ing
    -0.71
    imental
    -0.69
    oln
    -0.66
    POSITIVE LOGITS
     bankruptcy
    1.20
     restructuring
    1.14
     bankrupt
    1.11
    rupt
    1.08
     reorgan
    0.99
     filings
    0.95
     debtor
    0.87
     filing
    0.86
     restruct
    0.84
     trustee
    0.83
    Activations Density 0.011%

    No Known Activations