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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16411
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Joy"

    oai_token-act-pair · gpt-3.5-turbo
    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
    س
    -0.74
     strat
    -0.72
    Ranked
    -0.72
     Celt
    -0.69
     pl
    -0.69
     Marketable
    -0.68
    ellar
    -0.68
     plate
    -0.67
     supplemental
    -0.66
     drafted
    -0.64
    POSITIVE LOGITS
     Joy
    3.82
    Joy
    2.84
    joy
    2.18
     Joyce
    1.55
     Grace
    1.14
     joystick
    1.11
     Jess
    1.04
     Analog
    1.04
     Harmony
    1.00
     joy
    0.97
    Activations Density 0.013%

    No Known Activations