© 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. 10-ATT-KK
    11. 10899
    Prev
    Next
    INDEX
    Explanations

    phrases related to teamwork and objectives in competitive contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.09
    3:0.18
    4:0.20
    5:0.20
    6:0.02
    7:0.04
    8:0.05
    9:0.08
    10:0.02
    11:0.02
    Negative Logits
    >)
    -2.99
     ∼
    -2.85
    �
    -2.77
    vernment
    -2.74
    utterstock
    -2.68
     ≡
    -2.62
    >]
    -2.54
    '>
    -2.54
    †
    -2.53
    ��
    -2.50
    POSITIVE LOGITS
     analyse
    2.98
     alright
    2.92
     secondly
    2.90
     recognise
    2.89
     but
    2.87
     programme
    2.82
     organising
    2.81
     organise
    2.80
     rumours
    2.74
     afterwards
    2.68
    Activations Density 0.127%

    No Known Activations