© 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. 21595
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to rights and ways of access or entitlement

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.10
    3:0.04
    4:0.06
    5:0.04
    6:0.21
    7:0.21
    8:0.04
    9:0.05
    10:0.08
    11:0.08
    Negative Logits
     Sakuya
    -1.55
    ヴァ
    -1.46
    uably
    -1.40
    optim
    -1.35
    lier
    -1.35
    apore
    -1.34
     Tuls
    -1.33
    ugu
    -1.32
     preparations
    -1.31
     saturated
    -1.30
    POSITIVE LOGITS
     inheritance
    1.54
     property
    1.43
     Robotics
    1.43
    hander
    1.41
     inherit
    1.41
    avement
    1.34
     Enterprises
    1.33
     Movement
    1.29
     termination
    1.28
    eering
    1.26
    Activations Density 0.001%

    No Known Activations