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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10519
    Prev
    Next
    INDEX
    Explanations

    entities and actions related to social media and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.24
    1:0.02
    2:0.12
    3:0.09
    4:0.04
    5:0.05
    6:0.04
    7:0.04
    8:0.17
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
     Memphis
    -3.01
    Virginia
    -2.86
    Kansas
    -2.79
     Wichita
    -2.74
    Phase
    -2.71
     Virginia
    -2.70
            
    -2.65
     Durham
    -2.62
     Birmingham
    -2.60
    ichita
    -2.59
    POSITIVE LOGITS
    ibo
    5.59
     Sina
    3.94
     Siri
    3.72
     Qian
    3.30
     Yao
    3.25
     Zhu
    3.07
     Alibaba
    3.03
     Poké
    2.93
    �
    2.88
     selfies
    2.88
    Activations Density 0.004%

    No Known Activations