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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35788
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate efficiency and optimization in processes or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.05
    1:0.02
    2:0.05
    3:0.09
    4:0.03
    5:0.13
    6:0.02
    7:0.02
    8:0.11
    9:0.17
    10:0.16
    11:0.08
    Negative Logits
    iversary
    -1.26
    ーティ
    -1.23
     congratulations
    -1.23
    podcast
    -1.23
    ゴン
    -1.20
     Beir
    -1.18
    joined
    -1.17
    brother
    -1.17
    HAHAHAHA
    -1.17
    Congratulations
    -1.15
    POSITIVE LOGITS
     reactive
    1.45
     enforce
    1.43
     limiting
    1.39
     deter
    1.35
     mitigate
    1.33
     liability
    1.32
     inefficient
    1.30
     ripple
    1.29
     prevents
    1.29
     discretionary
    1.28
    Activations Density 1.675%

    No Known Activations