© 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. 35910
    Prev
    Next
    INDEX
    Explanations

    references to transgender identities and issues related to gender

    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
    0:0.02
    1:0.04
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.47
    7:0.03
    8:0.03
    9:0.05
    10:0.08
    11:0.04
    Negative Logits
    WARD
    -1.33
     Vij
    -1.33
     Feast
    -1.28
     Likes
    -1.26
    KNOWN
    -1.26
    liest
    -1.24
     exaggeration
    -1.22
     discretion
    -1.18
     Sheep
    -1.16
     understatement
    -1.16
    POSITIVE LOGITS
    iever
    1.60
    ilit
    1.59
    xual
    1.55
    uration
    1.52
    aucas
    1.52
    iferation
    1.49
    ioxide
    1.49
    fusc
    1.49
    perse
    1.48
    assemb
    1.48
    Activations Density 0.008%

    No Known Activations