© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12500
    Prev
    Next
    INDEX
    Explanations

    numerical values representing the quantity of jobs created or affected by various investments or projects

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with job creation and employment opportunities

    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
    hess
    -0.74
    History
    -0.72
     Allaah
    -0.72
     notor
    -0.69
    achu
    -0.67
    history
    -0.65
    govtrack
    -0.65
    laws
    -0.64
    bard
    -0.62
    money
    -0.62
    POSITIVE LOGITS
     jobs
    1.15
     layoffs
    1.11
     tonnes
    1.00
     acres
    0.99
    MW
    0.98
     million
    0.97
     gig
    0.95
     additional
    0.94
     hectares
    0.94
     tons
    0.89
    Activations Density 0.186%

    No Known Activations