© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 21523
    Prev
    Next
    INDEX
    Explanations

    references to support and political candidates

    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
    0:0.15
    1:0.03
    2:0.19
    3:0.05
    4:0.03
    5:0.10
    6:0.08
    7:0.07
    8:0.12
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
     Juda
    -2.87
     Torres
    -2.86
    riot
    -2.83
    ict
    -2.78
    riots
    -2.73
     warehouse
    -2.73
     Peel
    -2.71
     Shanghai
    -2.71
     Gord
    -2.68
     warehouses
    -2.65
    POSITIVE LOGITS
     Akin
    6.96
     contrace
    3.75
     contraceptive
    3.71
     pregnancies
    3.63
     menstrual
    3.49
     pregnancy
    3.44
     rape
    3.43
     semen
    3.42
     reproductive
    3.41
     contraception
    3.40
    Activations Density 0.001%

    No Known Activations