© 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. 33305
    Prev
    Next
    INDEX
    Explanations

    names or titles associated with notable individuals or organizations

    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
    0:0.21
    1:0.12
    2:0.07
    3:0.05
    4:0.02
    5:0.07
    6:0.02
    7:0.01
    8:0.06
    9:0.10
    10:0.09
    11:0.11
    Negative Logits
    served
    -1.87
    saw
    -1.83
    fortunately
    -1.83
    forces
    -1.82
    identified
    -1.73
    were
    -1.73
    rose
    -1.69
    rising
    -1.68
    abb
    -1.66
    ounced
    -1.66
    POSITIVE LOGITS
     segregation
    1.48
     consortium
    1.44
     immigration
    1.41
     integration
    1.39
     Wall
    1.36
     NBN
    1.36
     arbitration
    1.35
     antioxid
    1.34
     industrial
    1.34
     Autom
    1.34
    Activations Density 0.021%

    No Known Activations