© 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. 33218
    Prev
    Next
    INDEX
    Explanations

    names of people and their references in the text

    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
    0:0.03
    1:0.01
    2:0.31
    3:0.10
    4:0.05
    5:0.03
    6:0.07
    7:0.05
    8:0.08
    9:0.04
    10:0.09
    11:0.09
    Negative Logits
    translation
    -1.68
    ldom
    -1.65
    netflix
    -1.37
    NOT
    -1.37
     overdue
    -1.36
    DATA
    -1.36
     overload
    -1.34
    pmwiki
    -1.34
     subversive
    -1.32
     dunno
    -1.29
    POSITIVE LOGITS
    [/
    1.82
    rha
    1.72
    rider
    1.57
     Jr
    1.55
    scl
    1.50
    ewski
    1.49
    eder
    1.49
     HW
    1.49
    �士
    1.49
     Kodi
    1.48
    Activations Density 0.004%

    No Known Activations