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

    Neuronpedia

    Jacobian LensNEW
    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. 4403
    Prev
    Next
    INDEX
    Explanations

    business-related terms related to mergers, acquisitions, and purchases

    oai_token-act-pair · gpt-3.5-turbo
    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
    icone
    -0.94
     dstg
    -0.78
    henko
    -0.77
    eh
    -0.76
    pmwiki
    -0.76
    jriwal
    -0.74
    é»Ĵ
    -0.74
    ilib
    -0.70
    soType
    -0.70
    Tip
    -0.70
    POSITIVE LOGITS
     assets
    0.92
     holdings
    0.91
     subsidiaries
    0.84
     subsidiary
    0.82
     WhatsApp
    0.77
     stake
    0.76
     controlling
    0.74
     shares
    0.73
     stakes
    0.72
     defunct
    0.72
    Activations Density 0.091%

    No Known Activations