© 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. 1-RES-JB
    11. 24044
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Spirit"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "spirit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nightmares
    -0.70
    âķIJâķIJ
    -0.66
    theless
    -0.66
     pse
    -0.62
     cracked
    -0.61
     Kessler
    -0.61
     PBS
    -0.61
    enegger
    -0.58
    MAL
    -0.58
     Turing
    -0.58
    POSITIVE LOGITS
    uality
    1.45
     Spirit
    1.10
    Spirit
    1.03
    ually
    0.97
    ual
    0.96
    uous
    0.86
    wagon
    0.85
    loo
    0.79
     Tracks
    0.77
    isphere
    0.77
    Activations Density 0.005%

    No Known Activations