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. 9-RES-JB
    6. 22065
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.65
     bottleneck
    -0.63
     barric
    -0.63
     wandering
    -0.62
     morp
    -0.61
    nels
    -0.61
     pacing
    -0.60
     Scand
    -0.60
     labyrinth
    -0.59
    running
    -0.59
    POSITIVE LOGITS
     congratulations
    1.76
     congratulate
    1.55
     praise
    1.54
     thank
    1.50
     congrat
    1.50
     gratitude
    1.47
     praises
    1.43
     congr
    1.43
     congratulated
    1.39
     grateful
    1.39
    Activations Density 0.915%

    No Known Activations