© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11978
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and activities, specifically involving worries about a particular political figure

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

    concerns related to political issues, particularly regarding Trump and government administration

    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
    0:0.01
    1:0.04
    2:0.07
    3:0.03
    4:0.01
    5:0.03
    6:0.05
    7:0.11
    8:0.33
    9:0.09
    10:0.04
    11:0.13
    Negative Logits
    ォ
    -1.16
     necklace
    -1.11
     multit
    -1.08
    wcsstore
    -1.07
    ITNESS
    -1.06
     kcal
    -1.06
     ANGEL
    -1.05
    20439
    -1.05
    BuyableInstoreAndOnline
    -1.05
    affe
    -1.03
    POSITIVE LOGITS
    termin
    1.34
    behind
    1.30
    owe
    1.23
    cause
    1.16
    oS
    1.12
    LINE
    1.11
    arers
    1.11
    soon
    1.09
    bably
    1.08
    terms
    1.05
    Activations Density 0.018%

    No Known Activations