© 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. 27888
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional reflections and social critiques

    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
    0:0.09
    1:0.13
    2:0.03
    3:0.04
    4:0.02
    5:0.37
    6:0.02
    7:0.02
    8:0.09
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
     Lic
    -1.88
    */(
    -1.75
     Membership
    -1.75
    Spider
    -1.70
    itamin
    -1.69
    employ
    -1.64
    cium
    -1.64
    cies
    -1.63
    venue
    -1.62
     Annotations
    -1.61
    POSITIVE LOGITS
    ��
    2.03
     nightmares
    1.94
     vain
    1.92
    velt
    1.90
     shudder
    1.88
     wonder
    1.79
     Kurd
    1.75
     Romero
    1.72
     doubt
    1.71
     remembering
    1.71
    Activations Density 0.098%

    No Known Activations