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. 8645
    Prev
    Next
    INDEX
    Explanations

    references to political events or gatherings

    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
    0:0.03
    1:0.03
    2:0.04
    3:0.04
    4:0.03
    5:0.05
    6:0.11
    7:0.38
    8:0.06
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
    pixel
    -1.25
    odic
    -1.18
    nikov
    -1.17
    organic
    -1.14
     encyclopedia
    -1.14
     iceberg
    -1.10
    ドラ
    -1.10
    aretz
    -1.09
    quant
    -1.07
    atts
    -1.05
    POSITIVE LOGITS
     convened
    1.37
     Attend
    1.27
     Caucus
    1.22
     hosted
    1.22
     Cain
    1.21
    aucuses
    1.20
     chaired
    1.19
     honoring
    1.14
     descended
    1.13
    announced
    1.13
    Activations Density 0.013%

    No Known Activations