© 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. 5-ATT-KK
    11. 41586
    Prev
    Next
    INDEX
    Explanations

    instances of military actions and their consequences involving various armed groups

    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
    2:0.08
    3:0.13
    4:0.07
    5:0.04
    6:0.03
    7:0.06
    8:0.05
    9:0.10
    10:0.19
    11:0.16
    Negative Logits
     TRI
    -1.20
     Canaver
    -1.08
    uga
    -1.07
    ivals
    -1.04
     Intervention
    -0.98
    ���
    -0.97
     americ
    -0.96
    ÃÂÃÂ
    -0.96
     pioneers
    -0.95
     adop
    -0.95
    POSITIVE LOGITS
    lde
    1.23
     Mub
    1.10
     Reuters
    1.08
    SHARE
    1.06
     Jazeera
    1.03
     runoff
    1.03
    dayName
    1.02
    Continue
    1.00
     disappearance
    1.00
     AFP
    0.99
    Activations Density 0.352%

    No Known Activations