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. 8480
    Prev
    Next
    INDEX
    Explanations

    words related to romantic relationships

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to romance and romantic relationships

    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
     WTC
    -0.85
    ensor
    -0.75
     Concent
    -0.69
    Stack
    -0.69
     Blocks
    -0.68
     Fork
    -0.68
     Container
    -0.67
     Glob
    -0.67
    ACC
    -0.66
     Shap
    -0.65
    POSITIVE LOGITS
     romance
    3.49
     romantic
    2.40
     rom
    2.38
     Romance
    1.94
     Romantic
    1.75
     flirt
    1.62
     erotic
    1.44
     friendship
    1.38
     dating
    1.36
     monog
    1.35
    Activations Density 0.031%

    No Known Activations