© 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. 9-ATT-KK
    11. 1538
    Prev
    Next
    INDEX
    Explanations

    discussions related to political organizations and events

    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
    0:0.07
    1:0.02
    2:0.09
    3:0.09
    4:0.03
    5:0.06
    6:0.04
    7:0.04
    8:0.36
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
     Tennessee
    -3.47
    Atlanta
    -3.44
     Braves
    -3.40
     Tampa
    -3.23
     Miami
    -3.21
     Sanford
    -3.19
    Miami
    -3.18
     Atlanta
    -3.15
     Lorenzo
    -3.10
     Pose
    -3.10
    POSITIVE LOGITS
     McGill
    5.05
     Qué
    3.58
     QC
    3.43
    loo
    3.21
     Scotia
    3.04
     behaviours
    2.99
     Peel
    2.95
     McMaster
    2.90
     Halifax
    2.86
     Objective
    2.75
    Activations Density 0.022%

    No Known Activations