© 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 EvalsExportsinterp-engineNEWAPI 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. 12272
    Prev
    Next
    INDEX
    Explanations

    words related to financial terms, specifically focusing on pensions

    oai_token-act-pair · gpt-3.5-turbo

    references to pension-related topics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    selves
    -0.80
    iPhone
    -0.72
    amber
    -0.68
    Magikarp
    -0.64
    oks
    -0.63
    lins
    -0.63
    doors
    -0.63
    iesta
    -0.62
    ambers
    -0.62
    alogue
    -0.62
    POSITIVE LOGITS
     pension
    0.95
     fund
    0.90
     pensions
    0.90
    ers
    0.85
     Pension
    0.82
     entitle
    0.80
     income
    0.78
     trustees
    0.78
     funds
    0.78
     payments
    0.78
    Activations Density 0.025%

    No Known Activations