© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28119
    Prev
    Next
    INDEX
    Explanations

    terms related to community and connections among people

    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
    0:0.06
    1:0.14
    2:0.07
    3:0.09
    4:0.02
    5:0.14
    6:0.04
    7:0.02
    8:0.09
    9:0.10
    10:0.08
    11:0.10
    Negative Logits
    �醒
    -1.81
    ynthesis
    -1.67
    nown
    -1.60
    ワン
    -1.57
    pection
    -1.55
     Helic
    -1.50
     hindsight
    -1.47
     Tes
    -1.39
    sych
    -1.38
    unn
    -1.38
    POSITIVE LOGITS
     enthusi
    1.69
     charism
    1.51
    SPONSORED
    1.45
    ient
    1.38
    Feel
    1.37
     selves
    1.37
     flair
    1.36
     thinkers
    1.36
     Rodham
    1.33
     obliged
    1.32
    Activations Density 0.000%

    No Known Activations