© 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. 13170
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'coupled' or 'together with'

    oai_token-act-pair · gpt-3.5-turbo

    the concept of coupling in various contexts

    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
    emi
    -0.94
    hov
    -0.73
    shr
    -0.72
    odan
    -0.71
    thing
    -0.71
    lain
    -0.70
    acco
    -0.68
    xia
    -0.67
    cients
    -0.67
    metic
    -0.67
    POSITIVE LOGITS
     coupled
    1.03
     juxtap
    0.77
     coupling
    0.76
     reluct
    0.74
     adolesc
    0.70
     showc
    0.69
    uced
    0.68
     antioxid
    0.68
     inexper
    0.67
     solves
    0.66
    Activations Density 0.005%

    No Known Activations