© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10916
    Prev
    Next
    INDEX
    Explanations

    topics related to bias and discrimination, especially in the context of gender and race

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.04
    2:0.14
    3:0.06
    4:0.05
    5:0.04
    6:0.18
    7:0.04
    8:0.04
    9:0.20
    10:0.03
    11:0.02
    Negative Logits
     Mortal
    -3.23
     Turtles
    -3.21
     lease
    -3.19
     LU
    -3.16
    APTER
    -3.15
    LU
    -3.15
     Evan
    -3.11
    VC
    -3.10
     Pett
    -3.08
    aiden
    -3.07
    POSITIVE LOGITS
     bias
    7.80
     biases
    7.33
     biased
    7.11
    biased
    6.48
     prejudices
    5.40
     prejud
    5.35
     unbiased
    4.92
     prejudice
    4.87
     skew
    4.68
     skewed
    4.49
    Activations Density 0.004%

    No Known Activations