Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19147
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological efficiency

    oai_token-act-pair · gpt-3.5-turbo

    references to efficiency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.97
    BuyableInstoreAndOnline
    -0.71
    FACE
    -0.71
    jong
    -0.69
     Heights
    -0.68
     Falk
    -0.67
     Sour
    -0.66
    ortium
    -0.66
    picture
    -0.64
    ker
    -0.64
    POSITIVE LOGITS
     efficiency
    1.09
    iencies
    1.06
     efficient
    0.91
     inefficient
    0.90
     allocation
    0.87
     utilization
    0.85
     combustion
    0.82
     duplication
    0.81
     throughput
    0.81
    efficiency
    0.81
    Activations Density 0.036%

    No Known Activations