© 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. 7926
    Prev
    Next
    INDEX
    Explanations

    critical commentary on societal issues, especially regarding media representation and power dynamics

    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
    0:0.05
    1:0.02
    2:0.05
    3:0.21
    4:0.04
    5:0.06
    6:0.02
    7:0.06
    8:0.04
    9:0.03
    10:0.32
    11:0.06
    Negative Logits
     enlarged
    -1.95
     improved
    -1.92
     additional
    -1.90
     strengthened
    -1.89
     enhancements
    -1.85
     unforeseen
    -1.84
     nearby
    -1.81
    fitted
    -1.76
    requires
    -1.76
     netted
    -1.71
    POSITIVE LOGITS
     :(
    2.46
     goddamn
    2.40
    !".
    2.27
     haha
    2.22
    %.
    2.22
     fucking
    2.21
    !!!!
    2.19
    !!!
    2.19
     FUCK
    2.15
     nowadays
    2.15
    Activations Density 1.028%

    No Known Activations