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. 5-ATT-KK
    6. 43566
    Prev
    Next
    INDEX
    Explanations

    repeated symbols or characters, indicating their significance or prominence in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.04
    1:0.02
    2:0.14
    3:0.09
    4:0.05
    5:0.03
    6:0.24
    7:0.05
    8:0.06
    9:0.04
    10:0.05
    11:0.13
    Negative Logits
     Mail
    -1.47
    ���
    -1.43
    ware
    -1.40
     Markets
    -1.39
     NETWORK
    -1.38
     VIEW
    -1.37
     Webs
    -1.37
     Hebdo
    -1.34
     Faces
    -1.34
     Paid
    -1.30
    POSITIVE LOGITS
     renovations
    1.42
     repairs
    1.39
    wright
    1.38
    yne
    1.36
     reborn
    1.35
     renovation
    1.32
     ventilation
    1.27
    udi
    1.26
     stret
    1.22
    rises
    1.22
    Activations Density 0.001%

    No Known Activations