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

    Neuronpedia

    Jacobian LensNEW
    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. 5-ATT-KK
    11. 43589
    Prev
    Next
    INDEX
    Explanations

    references to societal expectations and experiences related to motherhood, gender roles, and individual choices

    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
    0:0.03
    1:0.01
    2:0.18
    3:0.25
    4:0.11
    5:0.03
    6:0.03
    7:0.07
    8:0.04
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
     FIRE
    -1.58
    tumblr
    -1.56
     Clockwork
    -1.46
     CALL
    -1.38
     Candy
    -1.37
     Cobra
    -1.36
     DRAGON
    -1.35
     Luther
    -1.34
     Seymour
    -1.32
     IRC
    -1.31
    POSITIVE LOGITS
     anymore
    2.85
     nor
    2.62
    nor
    1.68
     necessarily
    1.67
    Enough
    1.53
     slightest
    1.53
    ��
    1.50
    imilar
    1.50
    Orig
    1.50
     confir
    1.49
    Activations Density 0.021%

    No Known Activations