© 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. 47264
    Prev
    Next
    INDEX
    Explanations

    references to population statistics or demographics

    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
    0:0.04
    1:0.03
    2:0.24
    3:0.06
    4:0.08
    5:0.11
    6:0.04
    7:0.04
    8:0.07
    9:0.06
    10:0.07
    11:0.11
    Negative Logits
     protocols
    -1.78
     motto
    -1.77
     firewall
    -1.75
    )?
    -1.72
     shutting
    -1.60
     BET
    -1.58
     Comedy
    -1.56
    istant
    -1.55
     heels
    -1.53
     envy
    -1.52
    POSITIVE LOGITS
    ��
    2.56
    etheless
    2.40
    uana
    2.01
    eligible
    1.92
    votes
    1.87
    ��
    1.84
    Downloadha
    1.81
    pure
    1.80
    ccording
    1.79
    uggets
    1.78
    Activations Density 0.000%

    No Known Activations