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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12403
    Prev
    Next
    INDEX
    Explanations

    keywords related to memorials and ceremonies

    oai_token-act-pair · gpt-3.5-turbo

    references to memorials and commemorative events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lomb
    -0.70
    ucket
    -0.70
    efficients
    -0.69
    conom
    -0.66
    inion
    -0.63
    keye
    -0.61
    EEK
    -0.60
     Felix
    -0.59
    lying
    -0.59
    absolute
    -0.58
    POSITIVE LOGITS
    brance
    1.01
    izes
    1.00
    izing
    0.98
     memorial
    0.97
    izers
    0.91
    itory
    0.91
     remembrance
    0.91
    ization
    0.90
    isers
    0.89
     plaza
    0.84
    Activations Density 0.014%

    No Known Activations