© 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. 12846
    Prev
    Next
    INDEX
    Explanations

    phrases related to completing tasks or procedures

    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
    0:0.10
    1:0.02
    2:0.11
    3:0.08
    4:0.05
    5:0.06
    6:0.02
    7:0.02
    8:0.17
    9:0.22
    10:0.06
    11:0.03
    Negative Logits
    20439
    -1.26
    ensed
    -1.17
    ibi
    -1.16
    ivered
    -1.16
    hari
    -1.14
    etus
    -1.12
    arij
    -1.09
    aminer
    -1.08
    ilities
    -1.07
    verty
    -1.05
    POSITIVE LOGITS
     QC
    1.32
    方
    1.05
    �
    1.02
     Hitman
    1.02
     Sop
    1.01
     upgrades
    0.97
     Edit
    0.96
     upkeep
    0.96
     apartheid
    0.94
     renovations
    0.94
    Activations Density 0.057%

    No Known Activations