© 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. 8-RES-JB
    11. 2408
    Prev
    Next
    INDEX
    Explanations

    mentions of hiring or being hired for various tasks or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to hiring or employment-related actions

    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
    ican
    -0.79
    iversal
    -0.78
    ocol
    -0.72
    ĸļ
    -0.69
    ique
    -0.68
    otropic
    -0.66
    oche
    -0.66
    phy
    -0.66
    oland
    -0.65
    orld
    -0.65
    POSITIVE LOGITS
     hired
    0.91
     mercenaries
    0.90
    glers
    0.88
     assistants
    0.86
    lings
    0.83
     hire
    0.79
     interns
    0.74
     hires
    0.72
     laborers
    0.72
    lasses
    0.70
    Activations Density 0.029%

    No Known Activations