© 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. 41721
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to political actions and legal matters

    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
    1:0.02
    2:0.11
    3:0.18
    4:0.07
    5:0.05
    6:0.07
    7:0.03
    8:0.07
    9:0.10
    10:0.14
    11:0.08
    Negative Logits
     {*
    -1.45
     beforehand
    -1.44
    IAS
    -1.33
    urations
    -1.32
    soc
    -1.31
    vation
    -1.29
    �醒
    -1.28
    Sov
    -1.24
     outwe
    -1.22
    };
    -1.19
    POSITIVE LOGITS
    ASHINGTON
    1.43
     watchdog
    1.32
    eki
    1.23
     Oversight
    1.22
    zens
    1.20
     Canberra
    1.20
     investigating
    1.19
     Ivanka
    1.18
     Judicial
    1.14
    joice
    1.14
    Activations Density 0.390%

    No Known Activations