© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3288
    Prev
    Next
    INDEX
    Explanations

    references to Buddhism and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to Buddhism and its key figures and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EA
    -0.74
     Canter
    -0.68
    heric
    -0.67
    ynt
    -0.66
    alcohol
    -0.64
    hips
    -0.62
    OLOGY
    -0.62
    ribly
    -0.62
     clipboard
    -0.61
     OU
    -0.61
    POSITIVE LOGITS
     Buddha
    1.36
     Dharma
    1.09
     Buddhism
    1.01
     Buddhist
    1.01
     Tao
    0.93
    dh
    0.93
     Budd
    0.92
     Laksh
    0.87
     bamboo
    0.86
     meditation
    0.83
    Activations Density 0.021%

    No Known Activations