© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 22330
    Prev
    Next
    INDEX
    Explanations

    words related to planning and executing tasks, specifically focusing on the word "implement."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of implementing or execution of plans and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubi
    -0.73
    ovies
    -0.69
    onna
    -0.65
    olini
    -0.65
    vation
    -0.63
    imaru
    -0.62
    azines
    -0.61
    asia
    -0.60
    otics
    -0.59
     Corpus
    -0.58
    POSITIVE LOGITS
     strategies
    0.82
    matically
    0.80
    iencies
    0.76
    alities
    0.75
    ulate
    0.74
     reforms
    0.73
     policies
    0.73
     mechanisms
    0.69
    measures
    0.68
    plementation
    0.68
    Activations Density 0.086%

    No Known Activations