© 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. 10264
    Prev
    Next
    INDEX
    Explanations

    expressions of community and interaction among users or groups

    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
    0:0.02
    1:0.01
    2:0.27
    3:0.08
    4:0.16
    5:0.03
    6:0.06
    7:0.08
    8:0.05
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
     disinteg
    -1.71
    fitted
    -1.57
     modeled
    -1.57
     overlapping
    -1.54
     predomin
    -1.51
     identical
    -1.50
     plates
    -1.49
     territ
    -1.49
     atro
    -1.46
     seating
    -1.45
    POSITIVE LOGITS
    ppa
    1.94
    icans
    1.90
    DERR
    1.89
    arers
    1.82
    orters
    1.75
    rouse
    1.73
    thouse
    1.69
    !",
    1.68
    oS
    1.67
    AAAA
    1.67
    Activations Density 0.001%

    No Known Activations