© 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. 23083
    Prev
    Next
    INDEX
    Explanations

    news and political terms related to global events and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to political and social issues related to governance and policy

    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
    0:0.11
    1:0.02
    2:0.08
    3:0.12
    4:0.05
    5:0.13
    6:0.07
    7:0.03
    8:0.14
    9:0.08
    10:0.08
    11:0.03
    Negative Logits
    bang
    -1.32
    ーテ
    -1.29
    TEXTURE
    -1.26
    ModLoader
    -1.25
     viz
    -1.19
    FML
    -1.19
    oké
    -1.18
    Shape
    -1.17
    Bloom
    -1.16
    umatic
    -1.16
    POSITIVE LOGITS
     Vital
    1.07
    wat
    1.03
     •
    1.02
     |
    1.01
     Tale
    0.98
    ently
    0.97
     Rev
    0.95
     updated
    0.95
    ensed
    0.94
     summed
    0.94
    Activations Density 0.275%

    No Known Activations