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

    Neuronpedia

    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. 13820
    Prev
    Next
    INDEX
    Explanations

    information related to gender pay disparities in companies

    oai_token-act-pair · gpt-3.5-turbo

    references to gender disparities in employment or pay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    yth
    -0.82
     horm
    -0.81
    Param
    -0.81
     Canaver
    -0.81
     prog
    -0.80
     proto
    -0.74
     Kissinger
    -0.73
    Scientists
    -0.72
    akespe
    -0.72
    Psy
    -0.72
    POSITIVE LOGITS
     retailer
    1.99
     retailers
    1.93
     shoppers
    1.92
     stores
    1.92
     Walmart
    1.91
     Stores
    1.84
     retail
    1.77
     store
    1.77
    stores
    1.72
     Macy
    1.71
    Activations Density 0.551%

    No Known Activations