© 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. 43431
    Prev
    Next
    INDEX
    Explanations

    terms related to personal relationships and significant connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.17
    1:0.02
    2:0.09
    3:0.11
    4:0.11
    5:0.03
    6:0.10
    7:0.04
    8:0.13
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
    exclusive
    -1.92
     Oops
    -1.75
     cautioned
    -1.71
     cautiously
    -1.70
    .)
    -1.64
     signaled
    -1.58
     undersc
    -1.55
     manually
    -1.51
    ensional
    -1.50
     termed
    -1.46
    POSITIVE LOGITS
    Favorite
    2.02
     etc
    1.97
    brance
    1.66
    isms
    1.65
    thood
    1.65
    ivities
    1.64
    isations
    1.61
    hyde
    1.56
    comings
    1.56
    ories
    1.55
    Activations Density 0.002%

    No Known Activations