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. 0-RES-JB
    6. 19646
    Prev
    Next
    INDEX
    Explanations

    religious terms or references

    oai_token-act-pair · gpt-3.5-turbo

    references to religious themes and discussions of religious liberties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nem
    -0.67
     balloon
    -0.67
     oy
    -0.66
     thereto
    -0.66
     jun
    -0.66
     carrots
    -0.65
    ibur
    -0.65
     broccoli
    -0.64
     oval
    -0.64
     kale
    -0.64
    POSITIVE LOGITS
    Rel
    3.72
    rel
    1.73
    REL
    1.54
     Rel
    1.30
    religious
    1.29
     REL
    1.29
    Rest
    1.21
     Religious
    1.17
    Christian
    1.17
     Religion
    1.16
    Activations Density 0.010%

    No Known Activations