© 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. 5-ATT-KK
    11. 20358
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes in political or social circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.27
    3:0.19
    4:0.12
    5:0.01
    6:0.03
    7:0.11
    8:0.06
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     plaintiff
    -1.27
     plaintiffs
    -1.20
     geographically
    -1.20
     workload
    -1.19
     Defendants
    -1.18
     defect
    -1.17
    ometric
    -1.14
    adj
    -1.12
    engers
    -1.11
     overload
    -1.11
    POSITIVE LOGITS
    QUI
    1.52
    cember
    1.44
    ourt
    1.42
    bnb
    1.39
    �
    1.39
    tre
    1.36
    borgh
    1.35
    wx
    1.29
    ��
    1.28
     Flavoring
    1.28
    Activations Density 0.514%

    No Known Activations