© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10632
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or accusations related to individuals or groups

    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
    1:0.03
    2:0.07
    3:0.07
    4:0.02
    5:0.03
    6:0.05
    7:0.05
    8:0.06
    9:0.27
    10:0.12
    11:0.17
    Negative Logits
    Comments
    -1.30
    Pokémon
    -1.26
    Size
    -1.25
     greets
    -1.21
    Discussion
    -1.21
    FILE
    -1.16
     unfolds
    -1.15
    ISE
    -1.14
    Ball
    -1.14
    oku
    -1.14
    POSITIVE LOGITS
     wounding
    1.48
     distortion
    1.35
     cannibal
    1.34
    grave
    1.30
     sabot
    1.30
     killing
    1.30
     gou
    1.26
     VAT
    1.25
     distortions
    1.18
     inflicting
    1.17
    Activations Density 0.011%

    No Known Activations