© 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. 3260
    Prev
    Next
    INDEX
    Explanations

    concepts related to dividends and shareholder profits

    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
    0:0.21
    1:0.02
    2:0.10
    3:0.11
    4:0.05
    5:0.06
    6:0.06
    7:0.06
    8:0.09
    9:0.09
    10:0.07
    11:0.01
    Negative Logits
     Herz
    -2.83
     museums
    -2.71
     Sloven
    -2.70
     archae
    -2.66
     Croatia
    -2.66
     sculpture
    -2.58
     HG
    -2.58
     Handler
    -2.55
     archaeologists
    -2.54
     Cele
    -2.47
    POSITIVE LOGITS
     dividend
    6.45
     dividends
    5.58
     reinvest
    3.98
     shareholder
    3.92
     EPS
    3.62
     shareholders
    3.35
     diluted
    3.30
     Buffett
    3.29
     penny
    3.19
     Dollar
    3.18
    Activations Density 0.001%

    No Known Activations