© 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. 10-RES-JB
    11. 769
    Prev
    Next
    INDEX
    Explanations

    instances of narrative progression or change

    oai_token-act-pair · gpt-3.5-turbo

    instances of financial distress or failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keyes
    -0.86
     teasp
    -0.81
    eps
    -0.78
    ãĤ¼ãĤ¦ãĤ¹
    -0.76
    utterstock
    -0.74
    eming
    -0.72
    joice
    -0.71
    ioxid
    -0.69
    ologue
    -0.69
    icrobial
    -0.69
    POSITIVE LOGITS
     layoffs
    1.07
     bankruptcy
    1.03
     disband
    1.02
     disagreements
    1.02
     negotiations
    0.99
     rumours
    0.95
     creditors
    0.93
     restructuring
    0.92
     cancellation
    0.91
     contractual
    0.91
    Activations Density 0.549%

    No Known Activations