© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 20554
    Prev
    Next
    INDEX
    Explanations

    phrases related to couples or coupling

    oai_token-act-pair · gpt-3.5-turbo

    references to "couples" and related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Downloadha
    -0.92
    66666666
    -0.77
    utherford
    -0.76
    schild
    -0.76
    70710
    -0.74
     guiActiveUnfocused
    -0.72
    aceutical
    -0.71
    iary
    -0.71
    heid
    -0.69
    icago
    -0.66
    POSITIVE LOGITS
     Cou
    1.40
    iple
    1.00
    riers
    0.96
    plets
    0.94
    plet
    0.92
    ples
    0.89
    gars
    0.87
    ple
    0.82
    reth
    0.81
    ç
    0.81
    Activations Density 0.006%

    No Known Activations