© 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. 13622
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and government

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

    repeated mentions of the word "more."

    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
    0:0.09
    1:0.04
    2:0.09
    3:0.05
    4:0.03
    5:0.08
    6:0.19
    7:0.06
    8:0.06
    9:0.06
    10:0.13
    11:0.07
    Negative Logits
    ーテ
    -1.38
    swer
    -1.30
    ngth
    -1.25
     Shack
    -1.25
    ��
    -1.23
    ument
    -1.22
    ��
    -1.18
     Defender
    -1.14
    ラン
    -1.12
    dfx
    -1.10
    POSITIVE LOGITS
    votes
    1.25
     nominations
    1.11
     paperwork
    1.11
     approvals
    1.10
     opioids
    1.08
    Cra
    1.07
    RESULTS
    1.02
     crowded
    1.01
     capacity
    0.99
     zoning
    0.97
    Activations Density 0.040%

    No Known Activations