© 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. 5-ATT-KK
    11. 44146
    Prev
    Next
    INDEX
    Explanations

    phrases about gender and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.09
    3:0.05
    4:0.17
    5:0.02
    6:0.07
    7:0.35
    8:0.02
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
    avering
    -1.56
     accur
    -1.53
     maintained
    -1.53
    attribute
    -1.51
     specifications
    -1.50
    urance
    -1.49
    urances
    -1.49
     definition
    -1.48
     dimensions
    -1.47
     formulas
    -1.46
    POSITIVE LOGITS
    DragonMagazine
    1.80
    Brave
    1.57
    ��
    1.56
     VIDEOS
    1.50
    Guest
    1.49
     Welcome
    1.37
     Encounter
    1.33
     Morning
    1.32
    aneers
    1.32
     GOODMAN
    1.31
    Activations Density 0.001%

    No Known Activations