© 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. 16031
    Prev
    Next
    INDEX
    Explanations

    compassionate and empathetic phrases focusing on empathy and understanding

    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
    0:0.07
    1:0.05
    2:0.08
    3:0.05
    4:0.03
    5:0.17
    6:0.08
    7:0.09
    8:0.04
    9:0.04
    10:0.17
    11:0.08
    Negative Logits
     exclusively
    -0.95
    atered
    -0.88
     historic
    -0.88
     era
    -0.87
     departure
    -0.85
    ivo
    -0.83
    hu
    -0.81
     settlement
    -0.81
    atar
    -0.81
     appointment
    -0.80
    POSITIVE LOGITS
    etheless
    1.21
     Squid
    1.05
     Seym
    0.97
     Clover
    0.96
     contrace
    0.96
    fw
    0.96
    rely
    0.93
     Lol
    0.91
     cannabin
    0.91
     ItemLevel
    0.89
    Activations Density 0.735%

    No Known Activations