© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 4976
    Prev
    Next
    INDEX
    Explanations

    specific references to death and mourning

    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
    2:0.33
    3:0.11
    4:0.04
    5:0.09
    6:0.02
    7:0.07
    8:0.05
    9:0.03
    10:0.07
    11:0.04
    Negative Logits
     rapes
    -2.85
     sneaking
    -2.50
     abuses
    -2.48
     prosecutions
    -2.43
     coercion
    -2.43
     stuffing
    -2.39
    mong
    -2.33
     coercive
    -2.33
     manipulation
    -2.29
     balk
    -2.27
    POSITIVE LOGITS
    RIP
    4.42
     condol
    3.89
     mourn
    3.75
     funeral
    3.56
     condolences
    3.49
     mourning
    3.48
    ributes
    3.29
     farewell
    3.23
     RIP
    3.20
     saddened
    3.07
    Activations Density 0.206%

    No Known Activations