© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3525
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or sarcastic remarks related to "thanks for nothing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.02
    2:0.04
    3:0.39
    4:0.04
    5:0.05
    6:0.03
    7:0.06
    8:0.04
    9:0.03
    10:0.11
    11:0.05
    Negative Logits
     marriages
    -2.11
     bonded
    -2.01
    ,"
    -1.98
     supreme
    -1.97
     neighbors
    -1.91
     fortun
    -1.90
    ,''
    -1.89
     blessed
    -1.89
     fortunate
    -1.86
     winters
    -1.86
    POSITIVE LOGITS
    ](
    3.98
    ?]
    3.90
    ]:
    3.82
    ].
    3.82
     ].
    3.61
    !]
    3.41
    ]."
    3.37
    ][
    3.34
    :]
    3.33
    ]
    3.23
    Activations Density 0.079%

    No Known Activations