© 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. 12-RES-JB
    11. 5097
    Prev
    Next
    INDEX
    Explanations

    phrases related to pension plans and investments

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    concepts related to pensions and retirement

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    alan
    -0.65
    alogue
    -0.63
     Ferry
    -0.62
     Vive
    -0.61
    Sensor
    -0.61
    Dispatch
    -0.61
    ologist
    -0.60
    ological
    -0.60
     Cable
    -0.60
    alle
    -0.60
    POSITIVE LOGITS
     pensions
    0.96
     savings
    0.94
     funds
    0.94
     liabilities
    0.90
    forts
    0.89
     age
    0.89
     fund
    0.88
     plans
    0.86
     benefits
    0.85
     contributions
    0.84
    Activations Density 0.050%

    No Known Activations