© 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. 10-RES-JB
    11. 9978
    Prev
    Next
    INDEX
    Explanations

    phrases that describe actions done efficiently or effectively

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that connect phrases or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.67
     Golf
    -0.63
     Framework
    -0.62
     Entry
    -0.61
    BIL
    -0.60
    FER
    -0.60
    lime
    -0.60
     AG
    -0.59
    hner
    -0.59
     Door
    -0.58
    POSITIVE LOGITS
     efficiently
    1.24
     cheaply
    1.13
     without
    1.07
     preferably
    0.95
     securely
    0.94
     uninterrupted
    0.91
     WITHOUT
    0.89
     unpredict
    0.88
     rarely
    0.88
     smoothly
    0.87
    Activations Density 0.228%

    No Known Activations