© 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. 14201
    Prev
    Next
    INDEX
    Explanations

    information related to political or governmental activities

    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
    0:0.05
    1:0.02
    2:0.06
    3:0.18
    4:0.04
    5:0.09
    6:0.13
    7:0.04
    8:0.08
    9:0.10
    10:0.10
    11:0.05
    Negative Logits
     ­
    -1.00
     deposit
    -0.83
     quotas
    -0.82
     possessions
    -0.79
     attainment
    -0.78
     themselves
    -0.76
     empt
    -0.74
     assembly
    -0.74
     slavery
    -0.74
     quota
    -0.73
    POSITIVE LOGITS
    Untitled
    1.12
    maxwell
    1.07
    eric
    0.99
    isoft
    0.97
    oğan
    0.96
    zsche
    0.96
    Description
    0.95
    gor
    0.95
    ccording
    0.94
    avascript
    0.92
    Activations Density 0.137%

    No Known Activations