© 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. 2-ATT-KK
    11. 13117
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by directions or positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.15
    3:0.06
    4:0.26
    5:0.04
    6:0.02
    7:0.03
    8:0.16
    9:0.09
    10:0.05
    11:0.02
    Negative Logits
    sted
    -1.33
    externalActionCode
    -1.30
    uploads
    -1.26
     Lazarus
    -1.23
     Morse
    -1.22
    >>>>>>>>
    -1.22
     Hew
    -1.22
     Diablo
    -1.20
    fleet
    -1.19
     Qiao
    -1.19
    POSITIVE LOGITS
     shoulders
    1.50
     slopes
    1.42
     heights
    1.39
     hills
    1.39
     toward
    1.37
     pockets
    1.36
     towards
    1.34
    erest
    1.34
    roups
    1.31
     leaning
    1.31
    Activations Density 0.007%

    No Known Activations