© 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. 14230
    Prev
    Next
    INDEX
    Explanations

    references to love and relationships with strong emotional connections

    oai_token-act-pair · gpt-3.5-turbo

    references to love and affection for others

    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
    •layer 1 - love

    No Comments

    Negative Logits
    SPONSORED
    -0.89
    illin
    -0.82
    agher
    -0.76
    arta
    -0.76
    arat
    -0.75
    sk
    -0.68
    util
    -0.67
    ajo
    -0.62
    Dispatch
    -0.61
    inges
    -0.61
    POSITIVE LOGITS
     loved
    1.03
     dearly
    0.90
     uncond
    0.87
    nesday
    0.77
    76561
    0.73
    ĸļ
    0.72
     liked
    0.71
     Trident
    0.70
     loving
    0.69
    itely
    0.69
    Activations Density 0.012%

    No Known Activations