© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43619
    Prev
    Next
    INDEX
    Explanations

    instances of the word "being" and its context related to actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.03
    2:0.09
    3:0.07
    4:0.09
    5:0.03
    6:0.12
    7:0.08
    8:0.05
    9:0.05
    10:0.10
    11:0.21
    Negative Logits
     royalties
    -1.57
     UCH
    -1.41
     stip
    -1.35
     FML
    -1.35
     superhuman
    -1.33
    humans
    -1.31
     moan
    -1.30
     rider
    -1.30
     lapt
    -1.30
     precept
    -1.29
    POSITIVE LOGITS
    naire
    1.50
    arij
    1.50
    linked
    1.49
    acea
    1.47
    hess
    1.45
    ixtures
    1.45
    weather
    1.42
    etch
    1.41
    ixture
    1.38
    annis
    1.36
    Activations Density 0.017%

    No Known Activations