© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 41726
    Prev
    Next
    INDEX
    Explanations

    unique and complex names or identifiers

    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
    0:0.01
    1:0.01
    2:0.06
    3:0.05
    4:0.05
    5:0.04
    6:0.45
    7:0.04
    8:0.04
    9:0.06
    10:0.08
    11:0.05
    Negative Logits
    ngth
    -1.39
    ificial
    -1.32
     intersection
    -1.32
    pection
    -1.26
    将
    -1.24
    perture
    -1.21
    HAEL
    -1.20
    rity
    -1.18
     dissatisfaction
    -1.18
     breadth
    -1.17
    POSITIVE LOGITS
    ovi
    1.54
    si
    1.45
    istan
    1.39
    achu
    1.37
    hai
    1.27
    li
    1.26
     Haku
    1.23
    yu
    1.22
    chen
    1.21
    pei
    1.20
    Activations Density 0.006%

    No Known Activations