© 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. 10011
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and connections between individuals or groups

    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
    2:0.08
    3:0.09
    4:0.21
    5:0.03
    6:0.02
    7:0.27
    8:0.03
    9:0.03
    10:0.09
    11:0.05
    Negative Logits
    inction
    -1.81
     comparison
    -1.59
    tackle
    -1.57
     versus
    -1.55
     vs
    -1.55
    iasis
    -1.51
     understatement
    -1.50
     contrasted
    -1.48
    atts
    -1.47
     simplicity
    -1.46
    POSITIVE LOGITS
    soType
    1.79
    ournal
    1.42
    lishes
    1.41
     voic
    1.40
    ernel
    1.39
    ACTED
    1.38
     scanner
    1.38
     solicit
    1.37
     receivers
    1.37
     hotline
    1.37
    Activations Density 0.002%

    No Known Activations