© 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. 6962
    Prev
    Next
    INDEX
    Explanations

    phrases with the structure "the first time"

    oai_token-act-pair · gpt-3.5-turbo

    references to events that are described as the "first time" something has occurred

    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
    ulk
    -0.72
    ribut
    -0.69
    atu
    -0.69
    ibaba
    -0.68
    omo
    -0.65
    pletion
    -0.64
    ffee
    -0.63
    ensibly
    -0.63
    hua
    -0.62
    eper
    -0.62
    POSITIVE LOGITS
     culprit
    0.88
     instances
    0.82
    pmwiki
    0.78
     phenomenon
    0.78
     vex
    0.75
     shenan
    0.73
     pecul
    0.72
     accol
    0.72
     controversy
    0.72
     troubling
    0.72
    Activations Density 0.060%

    No Known Activations