© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-ATT-KK
    11. 12393
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal critique and political debate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.05
    2:0.12
    3:0.11
    4:0.11
    5:0.08
    6:0.03
    7:0.19
    8:0.04
    9:0.02
    10:0.07
    11:0.03
    Negative Logits
    pleted
    -2.76
    umbn
    -2.58
     Completed
    -2.42
    isoft
    -2.35
    ukong
    -2.34
    arden
    -2.28
    guyen
    -2.25
    essor
    -2.23
    pletion
    -2.22
    umbnails
    -2.22
    POSITIVE LOGITS
     liberals
    3.70
     libertarians
    3.52
    their
    3.37
     conservatives
    3.35
     moderates
    3.26
     their
    3.21
    Their
    3.17
     THEIR
    3.17
    they
    3.11
     Conservatives
    3.11
    Activations Density 0.794%

    No Known Activations