© 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. 5-ATT-KK
    11. 44004
    Prev
    Next
    INDEX
    Explanations

    phrases related to maximizing efficiency or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.04
    3:0.06
    4:0.11
    5:0.05
    6:0.04
    7:0.39
    8:0.04
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
    enegger
    -1.64
    anmar
    -1.64
    �
    -1.63
    actionDate
    -1.62
    hement
    -1.58
    regular
    -1.49
    mma
    -1.47
    ーティ
    -1.46
    wagon
    -1.41
    REDACTED
    -1.40
    POSITIVE LOGITS
     savings
    2.00
     throughput
    1.86
     efficiency
    1.84
     profits
    1.78
     effic
    1.78
    iveness
    1.78
     productivity
    1.77
     benefit
    1.70
     maximum
    1.68
     superiority
    1.66
    Activations Density 0.003%

    No Known Activations