© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 45937
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss significant economic impacts or consequences

    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
    0:0.05
    1:0.02
    2:0.08
    3:0.11
    4:0.04
    5:0.07
    6:0.03
    7:0.04
    8:0.09
    9:0.11
    10:0.16
    11:0.15
    Negative Logits
    eli
    -1.12
     █
    -1.07
    ���
    -1.07
     fame
    -1.07
     Milo
    -1.07
    aten
    -1.03
     1895
    -1.01
    boards
    -0.99
     Sebast
    -0.96
    oz
    -0.94
    POSITIVE LOGITS
     Flavoring
    1.40
    arios
    1.12
    Weak
    1.11
     Spending
    1.03
     unilateral
    1.03
    Leaks
    1.02
    Moreover
    1.01
     Knock
    1.01
     outweigh
    1.01
     Governments
    1.00
    Activations Density 0.160%

    No Known Activations