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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43032
    Prev
    Next
    INDEX
    Explanations

    terms related to products and material properties

    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
    2:0.25
    3:0.19
    4:0.09
    5:0.05
    6:0.04
    7:0.04
    8:0.07
    9:0.07
    10:0.08
    11:0.06
    Negative Logits
    laughter
    -1.73
     contrad
    -1.54
     Zah
    -1.45
     Kills
    -1.44
     Enemy
    -1.39
    龍契士
    -1.38
     Meng
    -1.37
    although
    -1.36
    orously
    -1.34
     Qiao
    -1.33
    POSITIVE LOGITS
     outweigh
    1.81
     stayed
    1.76
     seemed
    1.70
     seems
    1.64
     remained
    1.56
     remains
    1.54
    oother
    1.52
     proved
    1.50
     disappears
    1.49
     becomes
    1.48
    Activations Density 0.561%

    No Known Activations