© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 18959
    Prev
    Next
    INDEX
    Explanations

    references to female characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.04
    1:0.05
    2:0.09
    3:0.05
    4:0.06
    5:0.06
    6:0.07
    7:0.06
    8:0.06
    9:0.07
    10:0.13
    11:0.21
    Negative Logits
     princess
    -3.12
     Princess
    -2.99
     decorations
    -2.75
     Patron
    -2.69
     royalty
    -2.68
     gifts
    -2.62
     Empress
    -2.62
     Birthday
    -2.62
     honors
    -2.58
    Prin
    -2.57
    POSITIVE LOGITS
    DATA
    2.56
    ��
    2.40
    afety
    2.38
    ostic
    2.36
     informants
    2.29
     Watts
    2.28
    earch
    2.25
     methamphetamine
    2.24
     ATF
    2.23
     anecdotal
    2.22
    Activations Density 0.000%

    No Known Activations