© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 16002
    Prev
    Next
    INDEX
    Explanations

    instances related to legal or official matters, especially involving transportation authorities and incidents

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Head Attr Weights
    0:0.05
    1:0.42
    2:0.04
    3:0.05
    4:0.03
    5:0.04
    6:0.08
    7:0.05
    8:0.04
    9:0.04
    10:0.08
    11:0.03
    Negative Logits
     CFR
    -2.59
    sonian
    -2.56
    bestos
    -2.43
     principally
    -2.33
     Plymouth
    -2.32
     assemb
    -2.30
     practicable
    -2.29
    ivably
    -2.25
     prospect
    -2.24
     burg
    -2.22
    POSITIVE LOGITS
    �
    3.37
     [+
    3.33
     Sana
    3.27
    ㅋㅋ
    3.25
    ㅋ
    3.04
    ☆
    2.94
     haha
    2.83
    �
    2.75
     Anime
    2.74
     Sakuya
    2.74
    Activations Density 0.030%

    No Known Activations