© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20983
    Prev
    Next
    INDEX
    Explanations

    instances of the word "boss" and related terms associated with authority or management

    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
    0:0.08
    1:0.05
    2:0.10
    3:0.05
    4:0.04
    5:0.04
    6:0.21
    7:0.04
    8:0.05
    9:0.26
    10:0.03
    11:0.02
    Negative Logits
     Ramadan
    -3.97
     HDMI
    -3.40
     Palmer
    -3.39
     Flavoring
    -3.35
    phthal
    -3.29
    �
    -3.26
    ocry
    -3.19
    nav
    -3.16
     Num
    -3.14
    HD
    -3.13
    POSITIVE LOGITS
     Boss
    9.45
    Boss
    8.28
    boss
    8.15
     boss
    6.71
     bosses
    6.67
     Briggs
    4.26
     Hank
    4.10
     Maz
    3.93
     Ax
    3.88
     Colossus
    3.79
    Activations Density 0.002%

    No Known Activations