Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20673
    Prev
    Next
    INDEX
    Explanations

    references to investigations and reports related to health authorities

    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
    0:0.16
    1:0.03
    2:0.15
    3:0.07
    4:0.04
    5:0.06
    6:0.05
    7:0.05
    8:0.22
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
     foreclosure
    -3.74
     Klan
    -3.23
    bleacher
    -3.20
    Kings
    -3.18
    riots
    -3.17
     Sheriff
    -3.08
    bernatorial
    -3.08
     Fargo
    -3.06
    paio
    -3.04
     rentals
    -3.02
    POSITIVE LOGITS
     WHO
    6.65
    WHO
    5.21
     Ebola
    4.09
     OECD
    4.03
     UNHCR
    3.91
     Nigeria
    3.81
     malaria
    3.69
     Geneva
    3.67
     epidem
    3.62
     Lancet
    3.61
    Activations Density 0.010%

    No Known Activations