© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 9029
    Prev
    Next
    INDEX
    Explanations

    words related to physical expressions of affection, particularly kisses

    oai_token-act-pair · gpt-3.5-turbo

    instances of kissing and expressions of affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -1.06
    IJ
    -0.78
    ifted
    -0.75
    icum
    -0.75
     Flavoring
    -0.69
     Forbes
    -0.67
    äºĶ
    -0.66
    DoS
    -0.64
    markets
    -0.62
    ancial
    -0.62
    POSITIVE LOGITS
     goodbye
    1.25
     kiss
    1.06
     passionately
    1.00
     Kiss
    0.98
    creen
    0.96
    kiss
    0.93
     kisses
    0.91
     Goodbye
    0.89
     kissing
    0.85
     kissed
    0.83
    Activations Density 0.038%

    No Known Activations