© 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. 14831
    Prev
    Next
    INDEX
    Explanations

    organizations, movements and concepts related to social justice, activism, and political ideologies

    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
    0:0.08
    1:0.08
    2:0.05
    3:0.05
    4:0.03
    5:0.09
    6:0.04
    7:0.08
    8:0.06
    9:0.14
    10:0.18
    11:0.08
    Negative Logits
     IPM
    -1.42
     exha
    -1.14
     Inventory
    -1.13
     emergency
    -1.12
     notifications
    -1.10
     initialization
    -1.10
     backup
    -1.10
     sensors
    -1.08
     allerg
    -1.08
     explan
    -1.06
    POSITIVE LOGITS
     Christianity
    1.39
    estine
    1.28
     Marxism
    1.28
     caric
    1.27
     persecuted
    1.25
     gays
    1.24
     Islam
    1.24
     alike
    1.23
     adherents
    1.23
     Christians
    1.23
    Activations Density 0.418%

    No Known Activations