© 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. 6034
    Prev
    Next
    INDEX
    Explanations

    economic trends and changes in numerical values related to growth or decline

    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
    0:0.20
    1:0.11
    2:0.06
    3:0.05
    4:0.05
    5:0.13
    6:0.04
    7:0.02
    8:0.10
    9:0.06
    10:0.05
    11:0.08
    Negative Logits
    NetMessage
    -1.50
     experien
    -1.47
     cultivating
    -1.45
     carving
    -1.44
     offering
    -1.44
    ゴン
    -1.42
     tours
    -1.41
    20439
    -1.39
    ocating
    -1.38
     obser
    -1.38
    POSITIVE LOGITS
     0
    1.61
     49
    1.57
    again
    1.57
    =~
    1.53
    ifully
    1.49
     39
    1.44
     89
    1.44
     58
    1.41
     33
    1.41
     ¥
    1.41
    Activations Density 0.006%

    No Known Activations