© 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. 47049
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs and convictions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.06
    3:0.06
    4:0.06
    5:0.02
    6:0.17
    7:0.25
    8:0.04
    9:0.04
    10:0.09
    11:0.09
    Negative Logits
    AAAA
    -1.46
     nudity
    -1.45
    ADS
    -1.41
    USD
    -1.37
    Topic
    -1.35
    RM
    -1.34
    binding
    -1.32
    aneous
    -1.30
     similarities
    -1.29
     lymph
    -1.27
    POSITIVE LOGITS
    ���
    1.90
     scapego
    1.58
    ��
    1.51
     retire
    1.39
     econom
    1.38
     confir
    1.31
     prosper
    1.29
    inea
    1.29
     stranded
    1.29
    itia
    1.28
    Activations Density 0.005%

    No Known Activations