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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 603
    Prev
    Next
    INDEX
    Explanations

    mentions of salaries and earnings in various contexts

    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
    0:0.06
    1:0.03
    2:0.15
    3:0.16
    4:0.05
    5:0.12
    6:0.02
    7:0.08
    8:0.05
    9:0.03
    10:0.17
    11:0.02
    Negative Logits
    soType
    -2.19
     irreversible
    -2.09
     discontin
    -1.95
     blockers
    -1.94
     safeguards
    -1.94
    apego
    -1.91
     derailed
    -1.91
    ogens
    -1.88
     warheads
    -1.88
     obstacles
    -1.88
    POSITIVE LOGITS
     salary
    3.45
     salaries
    3.42
     Salary
    3.01
     hourly
    2.67
     earning
    2.59
     earn
    2.59
     wages
    2.57
     earns
    2.54
     average
    2.52
     wage
    2.48
    Activations Density 0.098%

    No Known Activations