© 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. 21623
    Prev
    Next
    INDEX
    Explanations

    numerical descriptions of physical measurements

    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
    2:0.10
    3:0.04
    4:0.06
    5:0.02
    6:0.07
    7:0.40
    8:0.03
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     flashbacks
    -1.73
     celebrations
    -1.70
     Anniversary
    -1.70
     Bye
    -1.66
    ノ
    -1.65
    dule
    -1.62
     celebration
    -1.59
    orate
    -1.56
     condolences
    -1.55
    acci
    -1.53
    POSITIVE LOGITS
     ceilings
    1.89
     protr
    1.87
     tallest
    1.81
     shoulders
    1.73
     crou
    1.72
    shield
    1.71
     waist
    1.70
     slope
    1.69
     gorilla
    1.65
     tall
    1.62
    Activations Density 0.035%

    No Known Activations