© 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. 15020
    Prev
    Next
    INDEX
    Explanations

    proper nouns like names of individuals and places

    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
    1:0.03
    2:0.07
    3:0.09
    4:0.04
    5:0.10
    6:0.10
    7:0.06
    8:0.09
    9:0.10
    10:0.13
    11:0.05
    Negative Logits
     Filter
    -0.94
     MFT
    -0.93
     Romeo
    -0.92
     Decoder
    -0.92
     Caesar
    -0.91
    Magikarp
    -0.89
     Circuit
    -0.88
    LAN
    -0.88
     Logo
    -0.87
     sucks
    -0.86
    POSITIVE LOGITS
     sqor
    1.39
     ende
    1.21
     conclud
    1.04
    international
    1.02
    opian
    1.00
    sonian
    0.99
    orously
    0.98
    itely
    0.98
    CLASSIFIED
    0.97
    reports
    0.97
    Activations Density 0.477%

    No Known Activations