© 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. 11-RES-JB
    11. 6694
    Prev
    Next
    INDEX
    Explanations

    statements related to feelings of love and connection with others

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to love and relationships

    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
    adobe
    -0.69
     Nanto
    -0.68
     convergence
    -0.65
    iHUD
    -0.65
     salv
    -0.65
     rall
    -0.64
    DEBUG
    -0.63
    DEN
    -0.62
    FINEST
    -0.59
    Completed
    -0.59
    POSITIVE LOGITS
     whom
    1.21
    folk
    1.00
    soever
    0.95
     who
    0.92
     else
    0.92
     uncond
    0.92
    ÃŃs
    0.80
    who
    0.80
     inappropriately
    0.80
    imity
    0.80
    Activations Density 0.318%

    No Known Activations