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. 3-ATT-KK
    6. 10517
    Prev
    Next
    INDEX
    Explanations

    phrases related to destruction or damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.26
    4:0.02
    5:0.03
    6:0.08
    7:0.17
    8:0.04
    9:0.08
    10:0.07
    11:0.10
    Negative Logits
    soType
    -1.37
    ITNESS
    -1.37
    ORTS
    -1.31
    itness
    -1.22
    Coach
    -1.21
    ANI
    -1.19
    College
    -1.18
     LAT
    -1.17
    OHN
    -1.17
    edes
    -1.16
    POSITIVE LOGITS
     havoc
    1.46
     limb
    1.31
     dams
    1.27
     landfill
    1.26
     Fukushima
    1.23
     wasteland
    1.21
     Colossus
    1.20
     Ashes
    1.19
     inciner
    1.19
     wast
    1.19
    Activations Density 0.013%

    No Known Activations