© 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. 12975
    Prev
    Next
    INDEX
    Explanations

    instances of occurrences or references within a legislative or political context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to legislative bodies or political entities

    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
    0:0.03
    1:0.06
    2:0.06
    3:0.23
    4:0.02
    5:0.02
    6:0.13
    7:0.10
    8:0.07
    9:0.10
    10:0.06
    11:0.06
    Negative Logits
    anco
    -1.11
    onal
    -1.11
    ibe
    -1.07
     tsun
    -1.07
    ogy
    -1.03
    iru
    -1.03
    Transfer
    -1.02
    ushi
    -1.00
     VK
    -0.97
     Logged
    -0.95
    POSITIVE LOGITS
    FORMATION
    1.15
    sembly
    1.12
    owship
    1.10
     agre
    1.09
     senators
    1.06
    interstitial
    1.06
     Veter
    1.06
     Representatives
    1.05
    cade
    1.02
    ailability
    1.02
    Activations Density 0.005%

    No Known Activations