© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3472
    Prev
    Next
    INDEX
    Explanations

    expressions evaluating the worth of something, usually in relation to effort, waiting, money, or risk

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the value or worth of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OHN
    -0.72
    ariat
    -0.62
    ardo
    -0.61
    laws
    -0.60
    Department
    -0.59
    ACTED
    -0.59
    eming
    -0.57
     Ens
    -0.57
    Assistant
    -0.57
    peak
    -0.56
    POSITIVE LOGITS
     gamble
    1.08
     investment
    1.05
     effort
    1.03
     hassle
    0.95
     price
    0.94
     wait
    0.91
     bother
    0.88
    $$$$
    0.85
     sacrifice
    0.85
     bucks
    0.84
    Activations Density 0.103%

    No Known Activations