© 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. 10610
    Prev
    Next
    INDEX
    Explanations

    references to couples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of the word "couple"

    oai_token-act-pair · gpt-3.5-turbo
    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
    schild
    -0.73
    umbn
    -0.67
    ibaba
    -0.67
    DERR
    -0.65
    é¾
    -0.64
    éļ
    -0.64
     Directorate
    -0.62
     Flavoring
    -0.62
    resso
    -0.59
     Glob
    -0.58
    POSITIVE LOGITS
     divorced
    0.99
     married
    0.98
     wed
    0.95
     divor
    0.91
    hood
    0.87
    riages
    0.85
     couples
    0.84
    maid
    0.83
    ndra
    0.82
    ter
    0.78
    Activations Density 0.027%

    No Known Activations