© 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 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. 7-RES-JB
    11. 1681
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace and employer actions

    oai_token-act-pair · gpt-3.5-turbo

    references to employers and workplace-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Revival
    -0.65
    ioxide
    -0.64
    agra
    -0.62
     Nieto
    -0.62
     Strait
    -0.62
    ás
    -0.61
    yss
    -0.60
    eyes
    -0.60
     originals
    -0.60
     Kw
    -0.59
    POSITIVE LOGITS
    employ
    0.99
     Employ
    0.85
     employer
    0.83
    avement
    0.82
     unions
    0.80
    ighed
    0.79
     employers
    0.78
    hetical
    0.76
    aved
    0.76
     Advantage
    0.75
    Activations Density 0.024%

    No Known Activations