© 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. 19520
    Prev
    Next
    INDEX
    Explanations

    subjective opinions and evaluations related to social and political issues

    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
    0:0.01
    1:0.02
    2:0.04
    3:0.06
    4:0.08
    5:0.04
    6:0.03
    7:0.41
    8:0.05
    9:0.05
    10:0.06
    11:0.09
    Negative Logits
    ーティ
    -1.83
    letal
    -1.55
    lance
    -1.53
    ecycle
    -1.52
    gallery
    -1.50
    ヘ
    -1.46
    deep
    -1.44
    ы
    -1.41
    �
    -1.39
    udi
    -1.37
    POSITIVE LOGITS
     propositions
    1.79
     convincing
    1.77
     proposition
    1.71
     bogus
    1.70
     convince
    1.64
     conclusive
    1.58
     spurious
    1.56
     unbiased
    1.55
     convinced
    1.54
     falsehood
    1.52
    Activations Density 0.023%

    No Known Activations