© 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. 7596
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to serious accusations or investigations

    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
    0:0.02
    1:0.02
    2:0.11
    3:0.15
    4:0.02
    5:0.03
    6:0.04
    7:0.08
    8:0.16
    9:0.11
    10:0.07
    11:0.13
    Negative Logits
     certific
    -1.06
     Chambers
    -0.93
     Sr
    -0.92
     Got
    -0.90
     Hartford
    -0.90
     Emb
    -0.90
    Gall
    -0.90
     examines
    -0.90
     UCLA
    -0.89
     Copyright
    -0.88
    POSITIVE LOGITS
    iHUD
    1.25
    ouf
    1.07
    >[
    1.03
    dden
    1.01
    terday
    1.00
    alkyrie
    0.98
    uph
    0.97
     inaction
    0.96
    amaru
    0.96
    iling
    0.95
    Activations Density 0.016%

    No Known Activations