© 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. 15926
    Prev
    Next
    INDEX
    Explanations

    words related to community and security/safety in the context of group activities and societal well-being

    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
    0:0.04
    1:0.03
    2:0.07
    3:0.05
    4:0.31
    5:0.07
    6:0.02
    7:0.02
    8:0.10
    9:0.14
    10:0.05
    11:0.03
    Negative Logits
    listed
    -1.53
    aband
    -1.52
    abases
    -1.50
     raided
    -1.42
    aughters
    -1.39
    osures
    -1.38
    apeake
    -1.37
    updated
    -1.36
    heat
    -1.35
    ospons
    -1.34
    POSITIVE LOGITS
     humour
    1.89
    ��
    1.82
     disson
    1.82
     unity
    1.74
     orthodoxy
    1.74
     morality
    1.74
     familiarity
    1.71
     negativity
    1.70
     morals
    1.66
     empathy
    1.66
    Activations Density 0.011%

    No Known Activations