© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 18834
    Prev
    Next
    INDEX
    Explanations

    sentences expressing sincere gratitude or condolences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sincerity and 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
     Morph
    -0.73
     cycle
    -0.71
    aeus
    -0.71
     edge
    -0.71
    deg
    -0.70
     cycles
    -0.68
    hyd
    -0.66
     properties
    -0.66
     Knock
    -0.65
     edges
    -0.65
    POSITIVE LOGITS
     sincere
    3.39
     sincerely
    2.81
     sincerity
    2.34
     heartfelt
    2.32
     earnest
    1.94
     thoughtful
    1.62
     truthful
    1.44
     genuine
    1.42
     hearty
    1.33
     gratitude
    1.32
    Activations Density 0.036%

    No Known Activations