© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22844
    Prev
    Next
    INDEX
    Explanations

    phrases related to cheating and deception

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words that indicate forms of "cheating" or dishonest behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.03
    2:0.22
    3:0.03
    4:0.33
    5:0.04
    6:0.02
    7:0.02
    8:0.06
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
    ゴ
    -1.36
     answ
    -1.24
     Rush
    -1.23
     Falls
    -1.22
     setback
    -1.20
     Standing
    -1.19
     Samp
    -1.18
     Contra
    -1.17
     affirmation
    -1.17
    asio
    -1.16
    POSITIVE LOGITS
    rons
    1.50
    thren
    1.45
     palate
    1.38
    estern
    1.34
    kees
    1.33
    kies
    1.32
    stakes
    1.27
    ttes
    1.26
    ritic
    1.25
    wald
    1.24
    Activations Density 0.008%

    No Known Activations