© 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. 28200
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dubbed" and its variations, indicating names or labels given to individuals or events

    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
    1:0.02
    2:0.06
    3:0.09
    4:0.13
    5:0.03
    6:0.05
    7:0.35
    8:0.03
    9:0.03
    10:0.07
    11:0.08
    Negative Logits
     causation
    -1.53
    mentioned
    -1.35
    Purchase
    -1.34
    hover
    -1.34
     dism
    -1.30
     placement
    -1.30
    istries
    -1.28
     comprehension
    -1.27
    istry
    -1.25
     navigation
    -1.25
    POSITIVE LOGITS
    iband
    1.73
    ッド
    1.51
    Í
    1.43
    黒
    1.37
    solete
    1.33
     louder
    1.32
    eni
    1.31
    ikers
    1.30
     loud
    1.29
     outlaw
    1.28
    Activations Density 0.003%

    No Known Activations