© 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. 16909
    Prev
    Next
    INDEX
    Explanations

    references to things considered sacred or divine

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "holy" or variations related to holiness

    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
    ILA
    -0.81
    respond
    -0.80
    llah
    -0.78
    */(
    -0.77
    resp
    -0.76
    CLA
    -0.74
    CAP
    -0.74
    OPA
    -0.73
    Pool
    -0.72
    PT
    -0.72
    POSITIVE LOGITS
     holy
    1.16
     pilgrimage
    0.91
     scripture
    0.90
     relics
    0.89
     gra
    0.89
     scriptures
    0.86
    holy
    0.80
     communion
    0.78
     rites
    0.78
     shrine
    0.77
    Activations Density 0.006%

    No Known Activations