© 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. 8-RES-JB
    11. 14118
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic policies and financial matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to economic issues and financial burdens

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Vaugh
    -0.81
    Legend
    -0.71
     confir
    -0.68
     Niet
    -0.67
     remem
    -0.61
     Metatron
    -0.61
    ĸļ
    -0.60
    ij士
    -0.59
    ãĥ¼ãĥ³
    -0.59
     experien
    -0.58
    POSITIVE LOGITS
     subsidies
    1.01
     subsid
    1.00
     subsidized
    0.95
     economically
    0.90
     subsidy
    0.87
     inefficient
    0.85
     disproportionately
    0.84
     incentiv
    0.84
     unsustainable
    0.82
     Medicare
    0.82
    Activations Density 1.687%

    No Known Activations