© 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. 22243
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sync" in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to synchronization processes or concepts

    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
    é¾
    -0.79
     Burger
    -0.76
    emouth
    -0.75
     Dough
    -0.74
     Charl
    -0.72
    ibur
    -0.70
     Hague
    -0.70
    wered
    -0.70
     Gill
    -0.68
     Cond
    -0.68
    POSITIVE LOGITS
     sync
    3.79
    sync
    3.23
     Sync
    3.08
    Sync
    2.75
     synchronization
    2.40
     synchron
    2.34
     synchronized
    2.05
    syn
    1.86
     syn
    1.85
    ync
    1.75
    Activations Density 0.027%

    No Known Activations