© 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. 10047
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships

    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
    0:0.02
    1:0.01
    2:0.16
    3:0.10
    4:0.30
    5:0.02
    6:0.06
    7:0.10
    8:0.04
    9:0.03
    10:0.07
    11:0.03
    Negative Logits
    Constructed
    -1.33
    iameter
    -1.16
     served
    -1.15
    Ranked
    -1.15
     pumped
    -1.14
    ocado
    -1.13
    Adds
    -1.12
    athered
    -1.12
     listen
    -1.11
     Lucia
    -1.10
    POSITIVE LOGITS
    ���
    1.47
     guiName
    1.37
    ��
    1.36
    chu
    1.36
     sufficiently
    1.35
     satisf
    1.31
     placebo
    1.31
    azo
    1.31
     Wrong
    1.29
     entropy
    1.28
    Activations Density 0.134%

    No Known Activations