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. 10-RES-JB
    6. 15648
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and thanks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude towards individuals or groups

    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
     Worse
    -0.78
     dystop
    -0.71
    ptive
    -0.71
    Abstract
    -0.71
    EStream
    -0.65
     indist
    -0.63
    Problem
    -0.63
    ption
    -0.63
    unin
    -0.62
     undesirable
    -0.62
    POSITIVE LOGITS
     generosity
    1.17
     generously
    1.16
     generous
    1.08
     tirelessly
    1.07
     hospitality
    1.00
     THANK
    0.96
     kindness
    0.94
     outp
    0.93
     patience
    0.91
     patronage
    0.91
    Activations Density 0.376%

    No Known Activations