© 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. 3-ATT-KK
    11. 6568
    Prev
    Next
    INDEX
    Explanations

    articles and determiners that introduce or specify nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.11
    3:0.16
    4:0.01
    5:0.02
    6:0.07
    7:0.10
    8:0.11
    9:0.18
    10:0.05
    11:0.08
    Negative Logits
    icer
    -1.51
    ���
    -1.36
    anyahu
    -1.30
    blow
    -1.29
    ovember
    -1.29
     broke
    -1.25
    ussed
    -1.24
    cca
    -1.23
    wered
    -1.21
    kered
    -1.19
    POSITIVE LOGITS
     assumption
    1.53
     whims
    1.43
     principles
    1.40
     subjective
    1.34
     Proced
    1.34
     referral
    1.29
     assumptions
    1.28
     pree
    1.28
     philosophies
    1.26
     Tradition
    1.25
    Activations Density 0.013%

    No Known Activations