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. 3-RES-JB
    6. 14981
    Prev
    Next
    INDEX
    Explanations

    words related to physical affection, specifically kissing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "kiss" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 3 - love

    No Comments

    Negative Logits
    é¾
    -0.94
    vernment
    -0.71
    ulhu
    -0.71
    ifted
    -0.70
    izoph
    -0.69
    IJ
    -0.68
     Administ
    -0.67
     Forbes
    -0.67
     DISTR
    -0.67
    irrel
    -0.67
    POSITIVE LOGITS
     kiss
    1.21
     goodbye
    1.20
     kisses
    1.16
    kiss
    1.13
     kissing
    1.08
     Kiss
    1.06
    creen
    1.02
     kissed
    1.00
    weed
    0.82
     farewell
    0.80
    Activations Density 0.009%

    No Known Activations