© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12316
    Prev
    Next
    INDEX
    Explanations

    words related to romantic love

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "love" and expressions of gratitude or affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 11 - love

    No Comments

    Negative Logits
    TPPStreamerBot
    -0.76
    ulhu
    -0.73
    å¸
    -0.71
    amas
    -0.68
    selves
    -0.65
    SPONSORED
    -0.65
    ħĭ
    -0.64
    icum
    -0.63
    arian
    -0.63
    Dispatch
    -0.62
    POSITIVE LOGITS
    birds
    1.26
    joy
    1.09
    making
    1.09
     affair
    1.07
     triangles
    1.00
     conqu
    0.95
     triangle
    0.93
    fest
    0.89
    fruit
    0.88
    bird
    0.88
    Activations Density 0.054%

    No Known Activations