© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10224
    Prev
    Next
    INDEX
    Explanations

    business-related terms such as "merger," "acquisition," and "takeover."

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to corporate mergers and acquisitions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    eh
    -0.73
    acus
    -0.69
    outh
    -0.67
    eva
    -0.67
    itudes
    -0.66
    icone
    -0.66
    otrop
    -0.65
    otropic
    -0.65
     Sta
    -0.64
     Ort
    -0.63
    POSITIVE LOGITS
     announcement
    1.07
     proposal
    0.99
     spree
    0.96
     agreement
    0.93
     decision
    0.89
     agreements
    0.88
     portfolio
    0.87
     restructuring
    0.87
     approvals
    0.85
     announcements
    0.85
    Activations Density 0.141%

    No Known Activations