© 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. 3-ATT-KK
    11. 10634
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to employment and work-related experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.24
    1:0.03
    2:0.11
    3:0.02
    4:0.08
    5:0.06
    6:0.06
    7:0.07
    8:0.04
    9:0.06
    10:0.13
    11:0.04
    Negative Logits
    RANT
    -1.18
     PDT
    -1.10
     rendition
    -1.05
     hysteria
    -1.04
     Amazon
    -1.04
     Billion
    -1.00
     Snowden
    -1.00
     verdict
    -1.00
     Balloon
    -0.99
     Mars
    -0.98
    POSITIVE LOGITS
     diligently
    1.37
    ework
    1.36
    assium
    1.28
    ateurs
    1.26
    enture
    1.24
    jobs
    1.22
    rower
    1.22
     ├
    1.21
     exha
    1.20
     srfAttach
    1.20
    Activations Density 0.068%

    No Known Activations