© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 26661
    Prev
    Next
    INDEX
    Explanations

    mentions of energy sources and related terms in the context of power generation

    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
    0:0.04
    1:0.02
    2:0.05
    3:0.04
    4:0.05
    5:0.03
    6:0.35
    7:0.05
    8:0.03
    9:0.04
    10:0.18
    11:0.08
    Negative Logits
    女
    -1.46
    SPONSORED
    -1.35
    urat
    -1.30
    ��
    -1.27
    DoS
    -1.23
     acknow
    -1.18
    rius
    -1.17
     Scal
    -1.17
    三
    -1.15
    stairs
    -1.14
    POSITIVE LOGITS
    ioxide
    1.60
    ヘ
    1.38
    ocaust
    1.28
     ignition
    1.27
     2020
    1.26
    ynthesis
    1.25
    riage
    1.23
     Shelter
    1.21
    enhagen
    1.20
    charg
    1.18
    Activations Density 0.015%

    No Known Activations