© 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. 8523
    Prev
    Next
    INDEX
    Explanations

    references to "The Nation" publication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.02
    1:0.05
    2:0.12
    3:0.10
    4:0.05
    5:0.21
    6:0.11
    7:0.06
    8:0.09
    9:0.04
    10:0.04
    11:0.06
    Negative Logits
    enza
    -1.93
    lished
    -1.90
    escription
    -1.87
    pex
    -1.87
    zona
    -1.82
    uilt
    -1.74
    portion
    -1.74
    batch
    -1.74
    cribed
    -1.72
    psey
    -1.68
    POSITIVE LOGITS
     likes
    1.90
     envy
    1.41
     Newsletter
    1.41
    ��
    1.33
     navigation
    1.33
     occasional
    1.32
     affinity
    1.32
     Athletics
    1.29
    LGBT
    1.28
     senses
    1.28
    Activations Density 0.001%

    No Known Activations