© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14510
    Prev
    Next
    INDEX
    Explanations

    phrases related to working hard and completing tasks successfully

    oai_token-act-pair · gpt-3.5-turbo

    expressions of effort and achievement related to work or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iru
    -0.68
    ittered
    -0.64
     remembers
    -0.62
    aneously
    -0.62
    itty
    -0.62
    Pierre
    -0.61
    window
    -0.60
    rish
    -0.60
    ives
    -0.59
     Allied
    -0.58
    POSITIVE LOGITS
     lately
    1.03
     since
    0.81
     countless
    0.81
     sufficiently
    0.75
     hitherto
    0.73
     griev
    0.73
     previously
    0.72
     recently
    0.70
     innumerable
    0.69
     kindly
    0.66
    Activations Density 0.641%

    No Known Activations