© 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. 1-RES-JB
    11. 10471
    Prev
    Next
    INDEX
    Explanations

    economic terms related to incentives

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to incentives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rooms
    -0.86
    rup
    -0.78
    nee
    -0.77
    agn
    -0.76
    angers
    -0.75
    asp
    -0.70
    gaard
    -0.70
    mac
    -0.69
    thing
    -0.68
    âĢ²
    -0.68
    POSITIVE LOGITS
     incentive
    1.42
     incent
    1.27
     incentives
    1.26
     incentiv
    1.14
     compensation
    0.94
     rewarded
    0.94
     compens
    0.87
     guiActiveUn
    0.86
     compel
    0.85
     induce
    0.82
    Activations Density 0.011%

    No Known Activations