© 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. 0-RES-JB
    11. 4892
    Prev
    Next
    INDEX
    Explanations

    words related to love and affection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "love" or related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 0 - love

    No Comments

    Negative Logits
     rhy
    -0.74
     beads
    -0.64
     Masters
    -0.64
     Sapphire
    -0.63
     Gem
    -0.62
     Saber
    -0.62
     matter
    -0.62
     rain
    -0.61
     Tea
    -0.61
     tea
    -0.61
    POSITIVE LOGITS
    OV
    4.52
    OVA
    2.26
    ov
    1.71
    oves
    1.48
    IK
    1.47
    ove
    1.35
    ova
    1.27
    oved
    1.24
    OFF
    1.22
    oval
    1.22
    Activations Density 0.006%

    No Known Activations