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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14137
    Prev
    Next
    INDEX
    Explanations

    instances of the word "happily"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of happiness and contentment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isman
    -0.69
    arnaev
    -0.69
     restraints
    -0.67
    iban
    -0.66
    inez
    -0.66
    arij
    -0.66
     weaknesses
    -0.66
    arta
    -0.64
    issors
    -0.63
    brance
    -0.63
    POSITIVE LOGITS
     happily
    0.94
    ï¸
    0.85
     gladly
    0.85
    ãĤ©
    0.83
    Ń·
    0.83
    bda
    0.79
    theless
    0.75
     rejoice
    0.73
     congratulations
    0.72
     cheers
    0.72
    Activations Density 0.007%

    No Known Activations