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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 41640
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the concept of 'mean' in varying contexts and nuances

    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
    0:0.02
    1:0.01
    2:0.11
    3:0.15
    4:0.09
    5:0.03
    6:0.10
    7:0.03
    8:0.03
    9:0.05
    10:0.06
    11:0.26
    Negative Logits
    ��
    -2.01
     motto
    -1.59
    andem
    -1.54
    fleet
    -1.53
     Panda
    -1.50
     Casual
    -1.49
    autical
    -1.48
     Fenrir
    -1.47
    ogi
    -1.47
    terday
    -1.46
    POSITIVE LOGITS
    thumbnails
    1.71
     anything
    1.59
    Loading
    1.57
    artz
    1.57
    Compat
    1.55
     partitions
    1.55
    Setup
    1.50
     setups
    1.48
     amendments
    1.41
     reproduce
    1.40
    Activations Density 0.002%

    No Known Activations