© 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. 28304
    Prev
    Next
    INDEX
    Explanations

    instances where something is discussed at the expense of someone or something else

    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
    0:0.03
    1:0.03
    2:0.05
    3:0.05
    4:0.13
    5:0.04
    6:0.03
    7:0.09
    8:0.04
    9:0.04
    10:0.06
    11:0.36
    Negative Logits
     reimburse
    -2.20
     McDonnell
    -2.15
     divest
    -2.07
     neglig
    -2.04
     liabilities
    -2.02
     wraps
    -1.98
     expenses
    -1.98
     incurred
    -1.97
     reimbursement
    -1.95
     reprint
    -1.89
    POSITIVE LOGITS
    ▬
    2.17
    �
    1.97
    rahim
    1.94
    lez
    1.92
    thood
    1.90
    agonists
    1.89
    selected
    1.87
    ategories
    1.87
    Comment
    1.86
    Profile
    1.82
    Activations Density 0.002%

    No Known Activations