© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 43637
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and expressions indicating frequency or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.09
    3:0.04
    4:0.09
    5:0.02
    6:0.14
    7:0.32
    8:0.03
    9:0.03
    10:0.06
    11:0.10
    Negative Logits
     Flavoring
    -1.93
    bush
    -1.47
     bid
    -1.45
    enture
    -1.44
    quartered
    -1.42
     contender
    -1.41
     shape
    -1.40
    qus
    -1.39
    minded
    -1.39
     minded
    -1.38
    POSITIVE LOGITS
    repeat
    1.79
     msec
    1.63
    ults
    1.48
     Archives
    1.48
     Dare
    1.42
    ッド
    1.36
    テ
    1.33
     Millennials
    1.33
     backups
    1.32
     Everyday
    1.32
    Activations Density 0.003%

    No Known Activations