© 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. 13079
    Prev
    Next
    INDEX
    Explanations

    language pertaining to governmental policies and district management

    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
    0:0.08
    1:0.03
    2:0.05
    3:0.07
    4:0.04
    5:0.05
    6:0.29
    7:0.03
    8:0.06
    9:0.20
    10:0.03
    11:0.02
    Negative Logits
     Prometheus
    -3.79
     Wilson
    -3.62
    Wilson
    -3.49
     Que
    -3.35
     Pu
    -3.25
     Reboot
    -3.22
    Rom
    -3.20
     Zo
    -3.13
    ingo
    -3.11
     Pel
    -3.10
    POSITIVE LOGITS
     District
    7.27
    District
    7.20
     district
    7.06
     districts
    6.58
     DISTRICT
    5.77
    dist
    4.28
     Berks
    3.82
     Township
    3.74
     Ward
    3.67
    sand
    3.62
    Activations Density 0.022%

    No Known Activations