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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 8759
    Prev
    Next
    INDEX
    Explanations

    references to mass shootings and related societal responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.06
    2:0.02
    3:0.08
    4:0.04
    5:0.07
    6:0.10
    7:0.36
    8:0.05
    9:0.06
    10:0.02
    11:0.04
    Negative Logits
    onyms
    -2.83
    ographs
    -2.74
    tml
    -2.30
    perties
    -2.26
    Ingredients
    -2.21
    Contents
    -2.17
    cellent
    -2.08
    adem
    -2.06
    Types
    -2.00
    ellect
    -1.97
    POSITIVE LOGITS
     Fukushima
    3.10
     earthquakes
    2.89
     doping
    2.70
     bombings
    2.70
     earthquake
    2.69
     assassination
    2.67
     bombing
    2.66
     assass
    2.64
     controversies
    2.63
     scandals
    2.58
    Activations Density 0.477%

    No Known Activations