© 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. 4-RES-JB
    11. 7172
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turbo

    phrases of gratitude and appreciation

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

    No Comments

    Negative Logits
    edin
    -0.98
    é¾
    -0.92
    orbit
    -0.90
    soDeliveryDate
    -0.89
    soever
    -0.80
    LAB
    -0.79
    Ops
    -0.77
    gypt
    -0.75
    aults
    -0.71
    Occup
    -0.71
    POSITIVE LOGITS
     example
    0.96
    gotten
    0.87
     awhile
    0.86
    geries
    0.85
    gery
    0.81
     goodness
    0.81
     pity
    0.78
     instance
    0.77
     bravery
    0.76
     inclusion
    0.76
    Activations Density 0.062%

    No Known Activations