© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 729
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements and weights

    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
    0:0.12
    1:0.18
    2:0.03
    3:0.02
    4:0.01
    5:0.29
    6:0.03
    7:0.03
    8:0.08
    9:0.07
    10:0.05
    11:0.02
    Negative Logits
     Gru
    -1.63
     delegated
    -1.44
    ses
    -1.43
     Galileo
    -1.42
     Iro
    -1.42
    organ
    -1.37
     Experiment
    -1.36
    surv
    -1.36
    selection
    -1.35
     Immun
    -1.35
    POSITIVE LOGITS
    taboola
    2.08
     pounds
    2.01
     miles
    2.00
     mile
    1.99
     yen
    1.88
     MPH
    1.86
     mph
    1.85
     dollar
    1.84
     pound
    1.83
     Yards
    1.83
    Activations Density 0.068%

    No Known Activations