© 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. 2769
    Prev
    Next
    INDEX
    Explanations

    mentions of prayers and related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to prayer and expressions of sympathy or condolences

    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
    mental
    -0.78
     retention
    -0.71
    onomy
    -0.69
    culosis
    -0.66
    stadt
    -0.65
    transfer
    -0.65
    relations
    -0.65
     Habit
    -0.65
    ership
    -0.65
    access
    -0.62
    POSITIVE LOGITS
     prayers
    1.34
    creen
    0.96
    mith
    0.94
    terday
    0.89
    peed
    0.84
    uits
    0.77
    chool
    0.74
    din
    0.73
    ipop
    0.73
    hops
    0.71
    Activations Density 0.025%

    No Known Activations