© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13895
    Prev
    Next
    INDEX
    Explanations

    references to religious or ritualistic practices

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to rituals and cultural practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spotlight
    -0.85
     Emails
    -0.82
     Expand
    -0.81
     Collider
    -0.80
     Recession
    -0.79
     Investor
    -0.78
     ISP
    -0.76
     Reviews
    -0.75
     CIS
    -0.75
     Comcast
    -0.73
    POSITIVE LOGITS
     ceremonial
    1.37
     ceremon
    1.30
     worshipped
    1.25
     vener
    1.23
     symbol
    1.22
     ornament
    1.17
     adorned
    1.16
     worn
    1.15
     decoration
    1.13
     symbolic
    1.12
    Activations Density 0.519%

    No Known Activations