© 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. 9-RES-JB
    11. 15443
    Prev
    Next
    INDEX
    Explanations

    words related to blessings

    oai_token-act-pair · gpt-3.5-turbo

    expressions of blessings or the concept of being blessed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apter
    -0.77
    */(
    -0.69
    oxic
    -0.69
    izoph
    -0.69
    pson
    -0.68
    raper
    -0.68
    owicz
    -0.67
    ickr
    -0.65
    issues
    -0.65
    anooga
    -0.64
    POSITIVE LOGITS
     bestowed
    0.97
     blessings
    0.95
     Bless
    0.94
     bless
    0.91
     Almighty
    0.89
    fully
    0.87
     forgiveness
    0.83
     blessing
    0.83
    eous
    0.81
    fulness
    0.76
    Activations Density 0.048%

    No Known Activations