© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 3376
    Prev
    Next
    INDEX
    Explanations

    accounts of suspicious deaths or investigations

    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
    0:0.16
    1:0.03
    2:0.28
    3:0.09
    4:0.03
    5:0.13
    6:0.04
    7:0.04
    8:0.04
    9:0.04
    10:0.04
    11:0.02
    Negative Logits
    otiation
    -2.74
     blackmail
    -2.74
     solidarity
    -2.54
     WTO
    -2.50
     GNU
    -2.49
    iannopoulos
    -2.44
     Mutant
    -2.42
     negotiation
    -2.40
     diplomacy
    -2.37
     renegoti
    -2.37
    POSITIVE LOGITS
     coroner
    5.38
     inquest
    5.05
     autopsy
    4.79
     coron
    3.96
    mortem
    3.84
     deceased
    3.71
     crem
    3.46
     burial
    3.38
     funeral
    3.34
     examiner
    3.28
    Activations Density 0.031%

    No Known Activations