© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19016
    Prev
    Next
    INDEX
    Explanations

    references to the National Broadband Network (NBN) and discussions surrounding its costs and services

    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
    0:0.02
    1:0.01
    2:0.06
    3:0.08
    4:0.06
    5:0.03
    6:0.05
    7:0.05
    8:0.04
    9:0.05
    10:0.33
    11:0.18
    Negative Logits
     UNESCO
    -1.69
    Offline
    -1.50
     Yelp
    -1.50
     Tolkien
    -1.48
     literary
    -1.44
     CLSID
    -1.42
     abst
    -1.41
    MpServer
    -1.39
    DragonMagazine
    -1.39
     satir
    -1.38
    POSITIVE LOGITS
    ��
    1.47
     lies
    1.40
     amnesty
    1.36
     promises
    1.32
    ansion
    1.29
    enium
    1.27
     Ribbon
    1.26
     handcuffs
    1.25
    lease
    1.22
    leasing
    1.21
    Activations Density 0.004%

    No Known Activations