© 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. 10-RES-JB
    11. 5713
    Prev
    Next
    INDEX
    Explanations

    words related to happiness or positive emotions

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "happy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 10 - joy

    No Comments

    Negative Logits
     Skinner
    -0.61
    coni
    -0.58
     UCH
    -0.57
    senal
    -0.56
     fixation
    -0.56
     Delta
    -0.55
     NCT
    -0.54
     arts
    -0.53
     Augusta
    -0.53
     veins
    -0.53
    POSITIVE LOGITS
    ening
    1.63
    ened
    1.57
    ily
    1.41
    iest
    1.31
    ens
    1.25
    eners
    1.08
    nown
    1.06
    iness
    1.06
    ier
    1.05
    en
    1.01
    Activations Density 0.036%

    No Known Activations