© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44128
    Prev
    Next
    INDEX
    Explanations

    specific mentions of casualties, especially focusing on children and officers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.14
    3:0.11
    4:0.14
    5:0.03
    6:0.05
    7:0.04
    8:0.18
    9:0.04
    10:0.12
    11:0.06
    Negative Logits
    same
    -2.02
    closed
    -1.60
    Same
    -1.59
    ablish
    -1.59
    ologies
    -1.52
    Allows
    -1.49
     refres
    -1.48
     same
    -1.46
     Same
    -1.46
     Sty
    -1.44
    POSITIVE LOGITS
    aspers
    1.65
    uana
    1.62
    inness
    1.61
    dinand
    1.60
    cussion
    1.60
    vre
    1.58
    ��
    1.58
     Voices
    1.54
     UNHCR
    1.51
     pee
    1.49
    Activations Density 0.001%

    No Known Activations