© 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. 3-ATT-KK
    11. 12859
    Prev
    Next
    INDEX
    Explanations

    language related to online search, databases, and technology tools

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

    words related to searching and search actions

    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
    0:0.33
    1:0.03
    2:0.04
    3:0.03
    4:0.06
    5:0.06
    6:0.09
    7:0.06
    8:0.04
    9:0.04
    10:0.13
    11:0.04
    Negative Logits
    alid
    -1.49
    adas
    -1.49
    lain
    -1.48
    aran
    -1.48
    rez
    -1.43
    unal
    -1.39
     Ambrose
    -1.35
    arian
    -1.33
    quin
    -1.31
    arat
    -1.31
    POSITIVE LOGITS
    ゴン
    1.50
    ipop
    1.40
    utters
    1.36
     Unleashed
    1.36
    ashtra
    1.34
     Pepe
    1.28
     snapping
    1.27
     elves
    1.26
    ��
    1.24
     Golf
    1.22
    Activations Density 0.008%

    No Known Activations