© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5366
    Prev
    Next
    INDEX
    Explanations

    phrases related to faith, protection, and prayers

    oai_token-act-pair · gpt-3.5-turbo

    content related to prayer and spiritual protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ranch
    -0.86
     Nato
    -0.78
    vernment
    -0.73
    Enlarge
    -0.72
     regional
    -0.71
     OECD
    -0.69
    African
    -0.68
     internationally
    -0.68
     Historically
    -0.67
     businesses
    -0.67
    POSITIVE LOGITS
    HAHAHAHA
    1.15
     bliss
    1.13
     FUCK
    1.11
     agony
    1.09
     fucking
    1.06
     hereby
    1.05
    REDACTED
    1.04
     fuck
    1.02
     goddamn
    1.02
     hilar
    1.01
    Activations Density 0.908%

    No Known Activations