© 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. 10-RES-JB
    11. 11583
    Prev
    Next
    INDEX
    Explanations

    references to mythological gods and goddesses across different cultures

    oai_token-act-pair · gpt-3.5-turbo

    references to deities and goddesses across various mythologies

    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
    Dispatch
    -0.90
    ateurs
    -0.86
    STD
    -0.86
    igslist
    -0.83
     DSM
    -0.81
    professional
    -0.80
    lease
    -0.80
    Marginal
    -0.78
    Internet
    -0.78
     VICE
    -0.78
    POSITIVE LOGITS
     deities
    1.64
     deity
    1.61
     goddess
    1.59
     gods
    1.47
     Goddess
    1.41
     Osiris
    1.32
     celestial
    1.31
     Deity
    1.30
     divine
    1.30
     Zeus
    1.27
    Activations Density 0.557%

    No Known Activations