© 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. 33233
    Prev
    Next
    INDEX
    Explanations

    phrases indicating vertical movement or position changes

    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
    0:0.11
    1:0.01
    2:0.18
    3:0.04
    4:0.11
    5:0.02
    6:0.07
    7:0.08
    8:0.19
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    orman
    -1.50
    ité
    -1.45
    iologist
    -1.42
    exempt
    -1.40
    evidence
    -1.40
    cv
    -1.39
    ogi
    -1.36
    helle
    -1.33
    901
    -1.31
    ��
    -1.30
    POSITIVE LOGITS
     recess
    1.52
     throne
    1.49
    uberty
    1.47
     wings
    1.42
    emale
    1.39
     trough
    1.36
    ilaterally
    1.35
    astically
    1.35
     cycles
    1.35
     TAMADRA
    1.34
    Activations Density 0.002%

    No Known Activations