© 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. 37160
    Prev
    Next
    INDEX
    Explanations

    phrases that include the preposition "of"

    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
    0:0.01
    1:0.01
    2:0.11
    3:0.07
    4:0.21
    5:0.01
    6:0.06
    7:0.26
    8:0.03
    9:0.02
    10:0.07
    11:0.07
    Negative Logits
    ategory
    -1.42
    externalActionCode
    -1.38
    ertation
    -1.34
    #$
    -1.27
    ortment
    -1.26
    Mbps
    -1.24
     ILCS
    -1.23
     Zup
    -1.22
    WHO
    -1.22
    SourceFile
    -1.22
    POSITIVE LOGITS
    acan
    1.33
     nascent
    1.27
    force
    1.21
     Artemis
    1.21
     fres
    1.15
     Echoes
    1.14
     Arrow
    1.13
     newfound
    1.12
     sovere
    1.12
     curtains
    1.11
    Activations Density 0.064%

    No Known Activations