© 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. 40636
    Prev
    Next
    INDEX
    Explanations

    expressions of intent or purpose, particularly involving the word "to"

    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
    0:0.02
    1:0.01
    2:0.07
    3:0.05
    4:0.04
    5:0.02
    6:0.09
    7:0.33
    8:0.05
    9:0.03
    10:0.07
    11:0.17
    Negative Logits
    �
    -1.49
     Donation
    -1.49
    Especially
    -1.47
    ernels
    -1.45
    lies
    -1.33
    nar
    -1.31
    Poor
    -1.27
    OIL
    -1.24
    hesda
    -1.21
    ayer
    -1.21
    POSITIVE LOGITS
     quizz
    1.48
    pheus
    1.43
     programmed
    1.37
     grapp
    1.34
    ibaba
    1.30
     fluent
    1.30
    authent
    1.27
     accredited
    1.24
    icho
    1.23
     grapple
    1.22
    Activations Density 0.007%

    No Known Activations