© 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. 0-RES-JB
    11. 22557
    Prev
    Next
    INDEX
    Explanations

    the word "lag" or related terms indicating delays or inefficiencies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to delays or shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hers
    -0.74
     Oath
    -0.73
    Radio
    -0.69
     Bones
    -0.67
    CTV
    -0.67
     Supp
    -0.64
     Jeremiah
    -0.64
    Person
    -0.63
    yes
    -0.63
     Carol
    -0.62
    POSITIVE LOGITS
     lag
    4.36
    lag
    2.25
     latency
    1.79
     Lag
    1.57
     drift
    1.24
     delay
    1.22
     stagn
    1.20
     sluggish
    1.18
     slowdown
    1.08
     stagnation
    1.04
    Activations Density 0.013%

    No Known Activations