© 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. 1-RES-JB
    11. 3591
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings of happiness and satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of joy and delight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 1 - happiness

    No Comments

    Negative Logits
    eworld
    -0.78
    alcohol
    -0.76
    organic
    -0.70
    vernment
    -0.67
    ifted
    -0.67
     downed
    -0.65
    helle
    -0.63
    xia
    -0.63
     Rhod
    -0.62
    otypes
    -0.62
    POSITIVE LOGITS
     delight
    1.24
    fully
    1.12
     pleasure
    0.95
    urous
    0.93
    iously
    0.91
     aston
    0.90
    ously
    0.89
    fulness
    0.86
    ishly
    0.85
    theless
    0.84
    Activations Density 0.006%

    No Known Activations