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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28484
    Prev
    Next
    INDEX
    Explanations

    expressions related to tragedies and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.07
    3:0.05
    4:0.09
    5:0.02
    6:0.06
    7:0.34
    8:0.02
    9:0.02
    10:0.13
    11:0.10
    Negative Logits
    ickr
    -1.81
    tyard
    -1.61
    uties
    -1.56
    erential
    -1.53
     descript
    -1.46
    fter
    -1.43
    ancies
    -1.42
    ioch
    -1.39
    orter
    -1.38
    icrobial
    -1.38
    POSITIVE LOGITS
     Fukushima
    1.87
     Titanic
    1.79
     Armageddon
    1.65
     Typhoon
    1.64
     injuries
    1.60
     Hurricane
    1.59
     Falling
    1.56
     inflicted
    1.54
     Deaths
    1.54
     Earthquake
    1.53
    Activations Density 0.010%

    No Known Activations