Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8754
    Prev
    Next
    INDEX
    Explanations

    mentions of girlfriends

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "girlfriend."

    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
    Not in Any Lists

    No Comments

    Negative Logits
    wise
    -0.67
    arth
    -0.63
    iers
    -0.63
     Chart
    -0.62
    otin
    -0.60
    .–
    -0.59
    Chart
    -0.59
     Component
    -0.59
    sbm
    -0.59
     Actions
    -0.59
    POSITIVE LOGITS
     girlfriend
    3.42
    girlfriend
    2.77
     girlfriends
    2.41
     boyfriend
    2.28
     fiance
    2.17
     wife
    2.01
     fian
    2.01
     roommate
    1.90
    irlfriend
    1.71
     mistress
    1.67
    Activations Density 0.011%

    No Known Activations