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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 15890
    Prev
    Next
    INDEX
    Explanations

    words related to strategic planning

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "strategic" in various contexts

    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
    DAY
    -0.86
    upon
    -0.84
    bell
    -0.83
    hner
    -0.83
    handle
    -0.83
    aday
    -0.81
    Wheel
    -0.79
    riots
    -0.77
    ATS
    -0.77
    ©¶æ¥µ
    -0.76
    POSITIVE LOGITS
    ategic
    0.99
     planning
    0.98
     importance
    0.94
     thinker
    0.92
     positioning
    0.92
     partnership
    0.91
     planner
    0.91
     partnerships
    0.91
     considerations
    0.90
     imperative
    0.90
    Activations Density 0.028%

    No Known Activations