© 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. 10-ATT-KK
    11. 14455
    Prev
    Next
    INDEX
    Explanations

    keywords related to personal traits and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.09
    2:0.06
    3:0.05
    4:0.07
    5:0.03
    6:0.09
    7:0.13
    8:0.03
    9:0.04
    10:0.07
    11:0.17
    Negative Logits
     Crack
    -2.39
     cracking
    -2.32
     cracked
    -2.24
    emate
    -2.23
     brawl
    -2.21
    shut
    -2.21
     lava
    -2.18
     arrests
    -2.18
    rection
    -2.15
     crackdown
    -2.14
    POSITIVE LOGITS
     traits
    4.97
     trait
    4.60
     qualities
    3.58
     characteristics
    3.51
     phenotype
    3.38
     attributes
    3.26
     characteristic
    3.06
     temperament
    3.04
     attractiveness
    2.96
     virtues
    2.88
    Activations Density 0.008%

    No Known Activations