© 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. 22155
    Prev
    Next
    INDEX
    Explanations

    references to roles and responsibilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    1:0.04
    2:0.06
    3:0.07
    4:0.05
    5:0.14
    6:0.03
    7:0.04
    8:0.14
    9:0.19
    10:0.08
    11:0.04
    Negative Logits
    pling
    -1.36
    oller
    -1.29
    ancies
    -1.28
    Cola
    -1.28
    itars
    -1.25
    ebin
    -1.25
    Downloadha
    -1.24
    č
    -1.24
    opal
    -1.23
    metry
    -1.21
    POSITIVE LOGITS
     discipl
    1.47
     memor
    1.36
     lia
    1.27
     rapport
    1.21
     conclud
    1.19
     arbit
    1.18
     Deter
    1.17
     affairs
    1.16
     medi
    1.15
     Anglo
    1.13
    Activations Density 0.073%

    No Known Activations