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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 10167
    Prev
    Next
    INDEX
    Explanations

    mentions of romantic or intimate actions like kissing

    oai_token-act-pair · gpt-3.5-turbo

    references to kissing and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -1.01
    ifted
    -0.74
    quickShipAvailable
    -0.73
    ulhu
    -0.70
    izoph
    -0.70
    æ©Ł
    -0.67
    IJ
    -0.67
     Administ
    -0.67
    ENCY
    -0.67
     DISTR
    -0.66
    POSITIVE LOGITS
     goodbye
    1.28
     kiss
    1.14
     Kiss
    1.07
     kisses
    1.06
     kissing
    0.99
    kiss
    0.99
    creen
    0.98
     kissed
    0.95
     passionately
    0.91
     Goodbye
    0.83
    Activations Density 0.026%

    No Known Activations