© 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. 24747
    Prev
    Next
    INDEX
    Explanations

    references to a specific person's perspective or actions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.09
    3:0.06
    4:0.12
    5:0.03
    6:0.10
    7:0.34
    8:0.02
    9:0.03
    10:0.09
    11:0.03
    Negative Logits
    Chel
    -1.79
    ukemia
    -1.72
    mp
    -1.68
    icum
    -1.64
    MT
    -1.63
    iqu
    -1.63
    reason
    -1.59
     Paste
    -1.58
     congr
    -1.55
    Merit
    -1.53
    POSITIVE LOGITS
     cursor
    2.14
     downwards
    2.04
     levers
    2.04
     inward
    2.01
     gaze
    1.97
     downward
    1.92
     backwards
    1.87
     curtains
    1.82
     wand
    1.80
     invisible
    1.79
    Activations Density 0.000%

    No Known Activations