© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3609
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and interpretations

    oai_token-act-pair · gpt-3.5-turbo

    references to the Bible and interpretations of its texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.85
    rontal
    -0.82
    nel
    -0.75
    umers
    -0.71
    iltr
    -0.71
    gpu
    -0.70
    ymm
    -0.70
    rils
    -0.70
    abiding
    -0.69
    abouts
    -0.69
    POSITIVE LOGITS
     scripture
    1.66
     scriptures
    1.58
     Koran
    1.54
     Scriptures
    1.52
     Bible
    1.51
     bible
    1.50
     Quran
    1.45
     Scripture
    1.41
     dictionary
    1.28
     Qur
    1.28
    Activations Density 0.331%

    No Known Activations