© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 12658
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial distress or bankruptcy

    oai_token-act-pair · gpt-3.5-turbo

    references to bankruptcy and related legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.91
    eq
    -0.78
    population
    -0.75
    resso
    -0.74
    alle
    -0.74
    enough
    -0.73
    rouse
    -0.72
    erd
    -0.70
    nesota
    -0.69
    atz
    -0.69
    POSITIVE LOGITS
     restructuring
    1.16
     bankrupt
    1.09
     bankruptcy
    1.09
     reorgan
    1.06
     filings
    1.02
    rupt
    0.97
     filing
    0.94
     trustee
    0.88
     debtor
    0.87
     restruct
    0.87
    Activations Density 0.030%

    No Known Activations