© 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. 9-RES-JB
    11. 3315
    Prev
    Next
    INDEX
    Explanations

    references to ancient religious texts

    oai_token-act-pair · gpt-3.5-turbo

    references to religious texts and scriptures

    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
    ttle
    -0.76
    leneck
    -0.75
    pless
    -0.75
    ggle
    -0.74
    gain
    -0.74
     srfAttach
    -0.73
    EStreamFrame
    -0.72
    docker
    -0.71
    yout
    -0.70
    assetsadobe
    -0.70
    POSITIVE LOGITS
     texts
    1.26
     manuscripts
    1.22
     manuscript
    1.18
     passages
    1.17
     scriptures
    1.17
     verses
    1.17
     written
    1.15
     verse
    1.14
     aloud
    1.14
     translated
    1.13
    Activations Density 0.360%

    No Known Activations