Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10646
    Prev
    Next
    INDEX
    Explanations

    instances of the word "boasts" and related phrases indicating possession or achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.05
    2:0.10
    3:0.07
    4:0.01
    5:0.05
    6:0.05
    7:0.07
    8:0.17
    9:0.18
    10:0.05
    11:0.12
    Negative Logits
     concludes
    -1.28
    eter
    -1.25
    onga
    -1.24
    IRC
    -1.19
    imaru
    -1.17
    imore
    -1.17
    Recommend
    -1.14
     IMAGES
    -1.07
    agher
    -1.06
    irc
    -1.06
    POSITIVE LOGITS
     superiority
    1.19
     backing
    1.18
     bragging
    1.12
     rooft
    1.11
     endorsements
    1.10
     sophistication
    1.08
     horns
    1.08
     mayors
    1.08
     capitals
    1.06
     entrances
    1.05
    Activations Density 0.009%

    No Known Activations