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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8485
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and social dynamics

    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
    0:0.14
    1:0.04
    2:0.04
    3:0.02
    4:0.30
    5:0.13
    6:0.06
    7:0.04
    8:0.03
    9:0.03
    10:0.07
    11:0.03
    Negative Logits
    etsk
    -1.72
    lt
    -1.71
     pardon
    -1.62
     analysts
    -1.62
     dated
    -1.55
    cill
    -1.54
    journal
    -1.51
    itures
    -1.50
     recall
    -1.48
    iture
    -1.48
    POSITIVE LOGITS
     hemor
    2.00
     SERVICE
    1.69
    ーク
    1.67
     pest
    1.65
    ulhu
    1.61
    �
    1.58
    WARE
    1.58
    ْ
    1.57
     boun
    1.54
    ▄
    1.53
    Activations Density 0.129%

    No Known Activations