© 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. 1432
    Prev
    Next
    INDEX
    Explanations

    words related to joy and positivity

    oai_token-act-pair · gpt-3.5-turbo

    words associated with joy or positive experiences

    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
    •layer 0 - joy

    No Comments

    Negative Logits
     sands
    -0.65
     Guitar
    -0.65
    itars
    -0.64
     Lit
    -0.62
     guitar
    -0.61
    TPPStreamerBot
    -0.60
     unt
    -0.60
     equival
    -0.59
     Rocks
    -0.59
     Nil
    -0.58
    POSITIVE LOGITS
    forced
    2.78
    joy
    2.28
    forcing
    2.17
    forces
    1.75
    force
    1.61
    large
    1.53
    forcer
    1.30
    forcement
    1.25
    humane
    1.24
    slave
    1.20
    Activations Density 0.042%

    No Known Activations