Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 7701
    Prev
    Next
    INDEX
    Explanations

    phrases related to death and its implications

    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
    0:0.05
    1:0.04
    2:0.12
    3:0.05
    4:0.05
    5:0.04
    6:0.29
    7:0.03
    8:0.03
    9:0.19
    10:0.03
    11:0.02
    Negative Logits
     rom
    -4.08
    displayText
    -3.99
     Robinson
    -3.35
    ctr
    -3.33
     pac
    -3.27
     Jordan
    -3.24
     prism
    -3.17
    PAC
    -3.15
    Plugin
    -3.15
    �
    -3.12
    POSITIVE LOGITS
     Death
    7.28
    Death
    6.59
    death
    6.58
     DEAD
    6.26
    Dead
    6.16
     Dying
    6.12
    dead
    6.10
     Die
    6.06
     death
    6.00
     Dead
    5.96
    Activations Density 0.018%

    No Known Activations