© 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. 4-RES-JB
    11. 12237
    Prev
    Next
    INDEX
    Explanations

    words related to flirtation and romantic interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of flirting or flirtatious behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pora
    -0.79
    CVE
    -0.75
    Region
    -0.71
    ifted
    -0.69
    HCR
    -0.68
    vation
    -0.68
    Reviewer
    -0.67
    EVA
    -0.67
    ulz
    -0.65
     thankful
    -0.64
    POSITIVE LOGITS
     flirt
    1.03
    irting
    0.87
    irted
    0.87
    hips
    0.82
     Draper
    0.82
    uously
    0.80
    uate
    0.73
     invitations
    0.70
    issance
    0.70
     Dres
    0.68
    Activations Density 0.016%

    No Known Activations