© 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. 18984
    Prev
    Next
    INDEX
    Explanations

    phrases associated with positions and titles within the political sphere

    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
    0:0.03
    1:0.01
    2:0.21
    3:0.07
    4:0.07
    5:0.02
    6:0.18
    7:0.13
    8:0.05
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    natureconservancy
    -1.62
    ensical
    -1.35
    itely
    -1.35
    earchers
    -1.35
    inarily
    -1.31
    weeney
    -1.29
    "]=>
    -1.28
    MAL
    -1.24
    Demand
    -1.23
    Leaks
    -1.23
    POSITIVE LOGITS
    ��
    1.36
     Caucasus
    1.25
     Azerb
    1.23
    ���
    1.23
     overpowered
    1.21
     expelled
    1.21
    �
    1.19
     Occ
    1.19
     Edit
    1.18
     Execution
    1.17
    Activations Density 0.003%

    No Known Activations