© 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. 10-ATT-KK
    6. 15083
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to cultural or social identity and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    2:0.03
    3:0.04
    4:0.13
    5:0.48
    6:0.02
    7:0.03
    8:0.02
    9:0.10
    10:0.02
    11:0.04
    Negative Logits
     Beginning
    -2.52
     Begin
    -2.52
     commence
    -2.48
     Continue
    -2.41
     shalt
    -2.41
     Valiant
    -2.40
    Continue
    -2.36
    orthy
    -2.27
     beginning
    -2.27
    pite
    -2.24
    POSITIVE LOGITS
     lacks
    3.88
    doesn
    3.64
     doesn
    3.45
     rarely
    3.44
     lacked
    3.27
     forbids
    3.23
     depended
    3.22
     cannot
    3.22
     seldom
    3.19
     relies
    3.17
    Activations Density 0.458%

    No Known Activations