© 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. 10010
    Prev
    Next
    INDEX
    Explanations

    phrases indicating distance or separation from a subject

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.11
    3:0.05
    4:0.11
    5:0.04
    6:0.07
    7:0.31
    8:0.04
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
     louder
    -1.52
     Feed
    -1.48
     encouragement
    -1.39
     omission
    -1.36
    グ
    -1.34
     gravy
    -1.33
     filler
    -1.32
    ocide
    -1.32
     Advertisement
    -1.31
     Forced
    -1.30
    POSITIVE LOGITS
     Greenwich
    1.98
    bledon
    1.81
     Hague
    1.75
    uart
    1.69
    auga
    1.65
     Avalon
    1.64
    hattan
    1.59
    campus
    1.56
     Windsor
    1.55
     nearest
    1.55
    Activations Density 0.000%

    No Known Activations