© 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. 43350
    Prev
    Next
    INDEX
    Explanations

    numeric data and statistical representations

    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
    0:0.06
    1:0.02
    2:0.10
    3:0.17
    4:0.09
    5:0.03
    6:0.05
    7:0.02
    8:0.07
    9:0.12
    10:0.11
    11:0.09
    Negative Logits
     Canaver
    -1.71
     reluct
    -1.67
    soDeliveryDate
    -1.59
    psey
    -1.55
    NetMessage
    -1.43
    mbuds
    -1.43
     withd
    -1.40
    eatures
    -1.37
    conservancy
    -1.36
    #$#$
    -1.35
    POSITIVE LOGITS
    Prev
    1.45
     avg
    1.43
     Avg
    1.39
     Average
    1.36
    Avg
    1.32
    Medium
    1.31
     Allows
    1.28
     (%)
    1.28
    Hig
    1.26
     Date
    1.25
    Activations Density 0.088%

    No Known Activations