© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 9998
    Prev
    Next
    INDEX
    Explanations

    contexts related to energy efficiency and storage systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.06
    3:0.50
    4:0.02
    5:0.07
    6:0.02
    7:0.04
    8:0.02
    9:0.02
    10:0.13
    11:0.01
    Negative Logits
     crashes
    -1.97
     Letters
    -1.90
     incidents
    -1.90
     irregularities
    -1.85
     grades
    -1.84
     twenties
    -1.83
     audits
    -1.81
     accidents
    -1.78
     births
    -1.77
     curls
    -1.76
    POSITIVE LOGITS
     savior
    3.01
     conduit
    2.96
     protector
    2.78
     centerpiece
    2.68
     helper
    2.66
     scapego
    2.58
     catalyst
    2.58
     totem
    2.48
     generator
    2.47
     ally
    2.44
    Activations Density 0.733%

    No Known Activations