© 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. 11838
    Prev
    Next
    INDEX
    Explanations

    words related to political parties, political affiliations, and political views

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

    phrases indicating public opinion on perceived threats

    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
    0:0.04
    1:0.06
    2:0.04
    3:0.02
    4:0.08
    5:0.31
    6:0.05
    7:0.06
    8:0.06
    9:0.05
    10:0.10
    11:0.07
    Negative Logits
     architectures
    -1.95
     archives
    -1.94
     prototypes
    -1.91
    leases
    -1.90
    devices
    -1.83
     outlaw
    -1.75
     platforms
    -1.71
     rend
    -1.70
     collectors
    -1.68
     bindings
    -1.66
    POSITIVE LOGITS
    Ranked
    2.35
     Gallup
    2.31
     Average
    2.19
    verages
    2.17
     Percentage
    2.17
     (-
    2.17
     (−
    2.16
    Percent
    2.15
     Unemployment
    2.11
     polled
    2.11
    Activations Density 0.306%

    No Known Activations