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. 343
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "thanks to."

    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
    ife
    -0.72
    anooga
    -0.71
    cair
    -0.68
    iveness
    -0.68
    okia
    -0.68
    uania
    -0.67
    answered
    -0.66
    quartered
    -0.65
    emo
    -0.65
    querque
    -0.65
    POSITIVE LOGITS
     tradition
    0.65
     Betsy
    0.65
     Luck
    0.64
     sheer
    0.63
     Wikipedia
    0.62
     virtue
    0.61
     wik
    0.61
     Pascal
    0.60
     advancements
    0.60
     Stacy
    0.58
    Activations Density 0.039%

    No Known Activations