Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 3292
    Prev
    Next
    INDEX
    Explanations

    references to rituals, especially those involving specific actions or events

    oai_token-act-pair · gpt-3.5-turbo

    concepts and discussions related to rituals and rites

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

    No Comments

    Negative Logits
    gets
    -0.88
    upon
    -0.80
     Pik
    -0.66
     Dollars
    -0.63
     Forbes
    -0.62
    olan
    -0.62
    utenant
    -0.61
    hner
    -0.61
    clud
    -0.61
    gow
    -0.60
    POSITIVE LOGITS
    istically
    1.06
     ritual
    1.02
     rituals
    1.01
     rites
    0.95
    ificial
    0.89
    istic
    0.88
     rite
    0.88
     Ritual
    0.85
    itual
    0.85
     invocation
    0.84
    Activations Density 0.009%

    No Known Activations