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. 0-RES-JB
    6. 16191
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.80
     Combine
    -0.63
    tower
    -0.62
     Dynamics
    -0.60
    cone
    -0.59
    Prop
    -0.59
    tail
    -0.58
    icles
    -0.57
    mix
    -0.57
    cpp
    -0.57
    POSITIVE LOGITS
     grateful
    3.46
     thankful
    3.14
     gratitude
    2.23
     glad
    1.83
     thanking
    1.78
     indebted
    1.63
     thanked
    1.58
     proud
    1.51
     fortunate
    1.47
     thank
    1.46
    Activations Density 0.013%

    No Known Activations