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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 23615
    Prev
    Next
    INDEX
    Explanations

    words related to productivity

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to productivity and its enhancement

    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
    anc
    -0.76
     Vet
    -0.69
    bors
    -0.66
    phan
    -0.65
    oval
    -0.63
    eh
    -0.63
    abel
    -0.63
    Bet
    -0.63
     aired
    -0.62
    elle
    -0.62
    POSITIVE LOGITS
     productivity
    3.74
     productive
    1.68
     efficiency
    1.54
     automation
    1.36
     workflow
    1.27
     competitiveness
    1.26
    efficiency
    1.26
     profitability
    1.26
     morale
    1.20
     creativity
    1.20
    Activations Density 0.014%

    No Known Activations