© 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. 21530
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the presence of items or activities in various contexts

    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
    2:0.09
    3:0.11
    4:0.14
    5:0.02
    6:0.18
    7:0.15
    8:0.03
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
     Indians
    -1.41
     backwards
    -1.32
     Deity
    -1.31
     stereotype
    -1.28
     subsistence
    -1.25
     backward
    -1.21
     Hindus
    -1.19
     Indian
    -1.19
     proving
    -1.18
    IRT
    -1.18
    POSITIVE LOGITS
    byn
    1.53
     �
    1.44
     volunte
    1.43
    agon
    1.34
     0004
    1.34
     actionGroup
    1.32
    itely
    1.30
    Ju
    1.30
     moderator
    1.29
    GBT
    1.29
    Activations Density 0.002%

    No Known Activations