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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10706
    Prev
    Next
    INDEX
    Explanations

    statements about political positions and dynamics

    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
    0:0.12
    1:0.02
    2:0.12
    3:0.08
    4:0.06
    5:0.10
    6:0.05
    7:0.11
    8:0.14
    9:0.05
    10:0.03
    11:0.07
    Negative Logits
    Ocean
    -2.58
    beard
    -2.47
    EStream
    -2.46
    estern
    -2.46
    perture
    -2.44
    cheat
    -2.42
     Realms
    -2.38
    olphin
    -2.35
    abeth
    -2.31
    ipples
    -2.28
    POSITIVE LOGITS
     BJP
    4.68
     Rahul
    4.46
     Kejriwal
    4.31
     Delhi
    4.22
     AAP
    4.06
     Gujarat
    3.65
     Sonia
    3.63
     Modi
    3.59
     Lok
    3.58
     RSS
    3.49
    Activations Density 0.160%

    No Known Activations