© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42796
    Prev
    Next
    INDEX
    Explanations

    metric units related to wind speed and pressure measurements

    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
    0:0.03
    1:0.02
    2:0.11
    3:0.05
    4:0.07
    5:0.03
    6:0.08
    7:0.28
    8:0.04
    9:0.05
    10:0.12
    11:0.08
    Negative Logits
     honoured
    -1.65
    版
    -1.55
     indemn
    -1.49
    staking
    -1.45
     secondly
    -1.43
    prises
    -1.43
     invitations
    -1.41
    anan
    -1.40
    gard
    -1.40
     Secondly
    -1.38
    POSITIVE LOGITS
     knots
    1.56
    motion
    1.45
    eways
    1.39
     Mechanical
    1.38
    heit
    1.37
     axle
    1.37
     gears
    1.36
    ERA
    1.35
     prope
    1.33
     wob
    1.33
    Activations Density 0.001%

    No Known Activations