© 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. 3-ATT-KK
    11. 12392
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical statistics related to financial and economic data

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    numerical statistics related to ownership and living conditions

    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
    0:0.04
    1:0.04
    2:0.20
    3:0.05
    4:0.04
    5:0.07
    6:0.07
    7:0.07
    8:0.13
    9:0.10
    10:0.08
    11:0.07
    Negative Logits
    版
    -1.31
    Together
    -1.25
    aper
    -1.24
    Haunted
    -1.20
    の魔
    -1.16
    NES
    -1.14
     preferably
    -1.13
     gotta
    -1.13
    nesota
    -1.13
     grate
    -1.09
    POSITIVE LOGITS
     standpoint
    1.64
     heights
    1.39
     (−
    1.30
     confines
    1.21
     Sever
    1.15
     extremes
    1.12
     Eag
    1.12
     Classification
    1.12
     declines
    1.12
     altogether
    1.11
    Activations Density 0.057%

    No Known Activations