© 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. 2-RES-JB
    11. 17583
    Prev
    Next
    INDEX
    Explanations

    instances related to different branches of Christianity and Judaism, particularly focusing on critical viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    references to religious beliefs and practices, specifically focusing on Catholicism and Christianity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    individual
    -0.75
    abet
    -0.75
    umm
    -0.66
    lev
    -0.62
    Lear
    -0.62
    une
    -0.61
    organ
    -0.60
    TAIN
    -0.60
    vol
    -0.60
    Neg
    -0.59
    POSITIVE LOGITS
    anship
    0.99
    opathy
    0.83
    ophobia
    0.79
    yip
    0.79
    imei
    0.78
    atism
    0.78
    ismo
    0.75
    jriwal
    0.74
    istry
    0.74
     anarchism
    0.72
    Activations Density 0.059%

    No Known Activations