© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37529
    Prev
    Next
    INDEX
    Explanations

    references to someone requesting something

    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
    0:0.07
    1:0.05
    2:0.09
    3:0.09
    4:0.09
    5:0.07
    6:0.10
    7:0.07
    8:0.08
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    将
    -1.96
    mad
    -1.89
    ilar
    -1.76
    �
    -1.75
    Haw
    -1.74
    aff
    -1.69
    �
    -1.69
    eness
    -1.67
     Verse
    -1.67
    height
    -1.65
    POSITIVE LOGITS
     conversions
    1.92
     manag
    1.91
     challengers
    1.89
     intermedi
    1.77
     doping
    1.76
     regul
    1.75
     beginners
    1.75
     cheaply
    1.74
     newcomers
    1.71
     accur
    1.70
    Activations Density 0.000%

    No Known Activations