© 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. 11517
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of "grace."

    oai_token-act-pair · gpt-3.5-turbo

    references to the show "Will and Grace."

    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
    Not in Any Lists

    No Comments

    Negative Logits
     breakout
    -0.66
     upgr
    -0.66
     analyst
    -0.63
    omet
    -0.62
    zone
    -0.62
     opposed
    -0.62
    OTE
    -0.61
    MET
    -0.60
    [_
    -0.60
     cat
    -0.60
    POSITIVE LOGITS
     Grace
    4.07
     grace
    1.90
     Faith
    1.24
     Emin
    1.18
     Joy
    1.17
     Glory
    1.14
     Grac
    1.13
     Griffith
    1.12
     Mercy
    1.11
    Gr
    1.10
    Activations Density 0.018%

    No Known Activations