© 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. 9-ATT-KK
    11. 13035
    Prev
    Next
    INDEX
    Explanations

    references to communal grief and expressions of sympathy

    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
    0:0.07
    1:0.02
    2:0.33
    3:0.13
    4:0.03
    5:0.12
    6:0.03
    7:0.07
    8:0.06
    9:0.02
    10:0.05
    11:0.02
    Negative Logits
    SpaceEngineers
    -2.68
    galitarian
    -2.50
    Techn
    -2.48
    config
    -2.47
    iencies
    -2.46
    tarians
    -2.43
    ensibly
    -2.41
    Magikarp
    -2.38
    opoly
    -2.37
     monopol
    -2.36
    POSITIVE LOGITS
     grieving
    6.17
     mourn
    5.56
     mourning
    5.50
     condol
    5.31
     grief
    5.10
     condolences
    4.88
     sorrow
    4.87
     memorial
    4.79
     sadness
    4.69
     remem
    4.65
    Activations Density 1.228%

    No Known Activations