© 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. 7-RES-JB
    11. 3113
    Prev
    Next
    INDEX
    Explanations

    the action of kissing

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -1.11
    quickShipAvailable
    -0.78
    ifted
    -0.77
     Forbes
    -0.72
    izoph
    -0.71
    bably
    -0.70
    DoS
    -0.70
    IJ
    -0.68
    lamm
    -0.68
     Flavoring
    -0.67
    POSITIVE LOGITS
     goodbye
    1.27
     kiss
    1.11
     kisses
    1.05
     Kiss
    1.00
    creen
    1.00
     kissing
    1.00
    kiss
    0.99
     passionately
    0.95
     kissed
    0.92
     farewell
    0.84
    Activations Density 0.032%

    No Known Activations