© 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. 11353
    Prev
    Next
    INDEX
    Explanations

    references to groups or categories of individuals, particularly in contexts related to victims or tragedies

    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
    2:0.05
    3:0.19
    4:0.02
    5:0.03
    6:0.08
    7:0.14
    8:0.06
    9:0.05
    10:0.06
    11:0.21
    Negative Logits
    Required
    -1.23
    SPONSORED
    -1.16
    ulhu
    -1.15
    Vision
    -1.12
    Program
    -1.12
     brilliance
    -1.08
    �
    -1.08
     glim
    -1.04
    Proof
    -1.04
    MIN
    -1.04
    POSITIVE LOGITS
    anmar
    1.50
     relatives
    1.38
    iblings
    1.33
    aceae
    1.32
     deceased
    1.27
    endants
    1.20
    ucc
    1.20
     severed
    1.19
     grieving
    1.19
     constituents
    1.18
    Activations Density 0.020%

    No Known Activations