Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13983
    Prev
    Next
    INDEX
    Explanations

    references to religious texts, particularly the word "Gospel" and writings related to it

    oai_token-act-pair · gpt-3.5-turbo

    references to religious texts, particularly the Gospels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.86
    alties
    -0.85
    aundering
    -0.82
    anyon
    -0.77
    rador
    -0.77
    govtrack
    -0.77
    yrinth
    -0.76
    rule
    -0.76
    netflix
    -0.74
    obbies
    -0.74
    POSITIVE LOGITS
    ospels
    1.04
     Gospel
    0.92
     Scriptures
    0.84
     scriptures
    0.84
     gospel
    0.82
     Compass
    0.80
     Savior
    0.78
     Reconstruction
    0.72
     Messiah
    0.70
     Bale
    0.70
    Activations Density 0.015%

    No Known Activations