© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14328
    Prev
    Next
    INDEX
    Explanations

    information regarding warnings and potential negative outcomes, particularly in political contexts

    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
    2:0.06
    3:0.02
    4:0.06
    5:0.03
    6:0.30
    7:0.04
    8:0.07
    9:0.23
    10:0.01
    11:0.03
    Negative Logits
    sylvania
    -3.65
     Polk
    -3.60
     Kushner
    -3.59
     Brad
    -3.35
     Eisen
    -3.33
    �
    -3.30
    thal
    -3.29
     Harrison
    -3.28
    negie
    -3.26
    Brad
    -3.22
    POSITIVE LOGITS
     Mu
    10.75
    Mu
    9.76
     MU
    7.58
     mu
    7.41
    mu
    6.90
    MU
    6.78
     Scully
    6.69
     Mau
    4.78
     Muhammad
    4.50
    Fu
    4.48
    Activations Density 0.005%

    No Known Activations