© 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. 13915
    Prev
    Next
    INDEX
    Explanations

    words related to law, legal proceedings, and court cases

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

    terms related to legal proceedings and court cases

    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
    0:0.01
    1:0.04
    2:0.08
    3:0.08
    4:0.02
    5:0.07
    6:0.08
    7:0.14
    8:0.09
    9:0.14
    10:0.08
    11:0.11
    Negative Logits
    ーク
    -1.29
    ォ
    -1.07
    オ
    -1.06
    VERTISEMENT
    -1.05
     Scandinav
    -1.02
    機
    -1.01
     stereotype
    -1.01
    �
    -1.01
    Poor
    -1.00
     Gleaming
    -0.99
    POSITIVE LOGITS
     prosecution
    1.39
     litigation
    1.32
     manslaughter
    1.30
     alleging
    1.30
     extradition
    1.30
     suing
    1.27
     prosecutions
    1.24
     proceedings
    1.22
     wrongful
    1.19
     infringement
    1.18
    Activations Density 0.139%

    No Known Activations