© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 12667
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving orders or commands

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.07
    2:0.09
    3:0.09
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
    alid
    -1.73
    lig
    -1.54
    aci
    -1.52
    lear
    -1.50
    tun
    -1.43
    accompanied
    -1.40
    announced
    -1.37
    otti
    -1.34
    loc
    -1.33
    bus
    -1.32
    POSITIVE LOGITS
     Dragonbound
    1.54
    ahime
    1.47
    ▒
    1.46
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    1.38
     Draper
    1.37
    BuyableInstoreAndOnline
    1.37
    ̶
    1.35
     Ruler
    1.35
     Lauder
    1.29
     Rankings
    1.27
    Activations Density 0.000%

    No Known Activations