© 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. 10-RES-JB
    11. 6609
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning a specific definition of marriage as being between a man and a woman

    oai_token-act-pair · gpt-3.5-turbo

    phrases asserting traditional views on marriage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    00007
    -0.74
     Transcript
    -0.70
    inventoryQuantity
    -0.69
    REF
    -0.67
     Staples
    -0.66
    ãĥ¯ãĥ³
    -0.64
     disapp
    -0.64
     Borders
    -0.63
    External
    -0.62
    Reloaded
    -0.61
    POSITIVE LOGITS
     woman
    1.49
     women
    1.47
     WOM
    1.23
     female
    1.21
     females
    1.20
    women
    1.18
     Woman
    1.18
     ladies
    1.14
     wife
    1.12
     girl
    1.12
    Activations Density 0.166%

    No Known Activations