© 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. 2-ATT-KK
    11. 21448
    Prev
    Next
    INDEX
    Explanations

    phrases involving authoritative commands or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    2:0.12
    3:0.06
    4:0.23
    5:0.13
    6:0.03
    7:0.03
    8:0.06
    9:0.16
    10:0.05
    11:0.03
    Negative Logits
    rag
    -1.35
     fracture
    -1.17
    mouth
    -1.17
    agger
    -1.17
     heroine
    -1.17
    mel
    -1.15
    イト
    -1.15
    ギ
    -1.14
     throb
    -1.12
     scrape
    -1.10
    POSITIVE LOGITS
    heit
    1.41
    ihad
    1.39
    ongyang
    1.39
    ento
    1.28
    matically
    1.21
     suppliers
    1.21
    ylum
    1.21
    ettings
    1.19
     DEFENSE
    1.19
     Nieto
    1.17
    Activations Density 0.004%

    No Known Activations