© 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. 5-ATT-KK
    11. 24725
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states and feelings

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.10
    1:0.11
    2:0.04
    3:0.04
    4:0.03
    5:0.19
    6:0.04
    7:0.04
    8:0.14
    9:0.05
    10:0.07
    11:0.10
    Negative Logits
    ModLoader
    -1.91
    ワン
    -1.81
    Synopsis
    -1.73
    Rail
    -1.73
    ��
    -1.69
    ¨
    -1.65
    �
    -1.65
    utory
    -1.60
    utsche
    -1.57
    VIDIA
    -1.55
    POSITIVE LOGITS
     anx
    1.58
     dice
    1.50
     subconscious
    1.48
    cha
    1.48
     fallacy
    1.40
     Monica
    1.38
     Whites
    1.37
     autonom
    1.36
     nervous
    1.35
     fall
    1.34
    Activations Density 0.006%

    No Known Activations