© 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. 40394
    Prev
    Next
    INDEX
    Explanations

    references to contract-related terminology

    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
    0:0.07
    1:0.11
    2:0.08
    3:0.07
    4:0.10
    5:0.09
    6:0.07
    7:0.07
    8:0.08
    9:0.07
    10:0.08
    11:0.06
    Negative Logits
    xtap
    -1.95
    gdala
    -1.71
    tyard
    -1.68
    enne
    -1.66
    Pref
    -1.64
    nos
    -1.60
    angular
    -1.59
    root
    -1.59
    ォ
    -1.58
    rir
    -1.57
    POSITIVE LOGITS
     Euros
    1.84
     libel
    1.82
     commitments
    1.72
     bogus
    1.70
     extortion
    1.69
     pensions
    1.68
     settlements
    1.66
     journalism
    1.66
     national
    1.65
     socialist
    1.64
    Activations Density 0.000%

    No Known Activations