© 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. 15326
    Prev
    Next
    INDEX
    Explanations

    references to protests or opposition

    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
    0:0.10
    1:0.04
    2:0.09
    3:0.05
    4:0.05
    5:0.05
    6:0.22
    7:0.04
    8:0.08
    9:0.17
    10:0.04
    11:0.02
    Negative Logits
     dru
    -4.09
     skiing
    -3.80
    omen
    -3.78
     Ski
    -3.62
     ski
    -3.54
     Druid
    -3.47
     Rai
    -3.46
     mountain
    -3.45
     Sau
    -3.41
     Sierra
    -3.36
    POSITIVE LOGITS
     GD
    9.99
    GD
    9.14
    gd
    5.84
     DG
    4.59
     Geh
    4.35
     McH
    4.12
     Maggie
    4.04
    ructose
    3.76
     TG
    3.63
     Gh
    3.56
    Activations Density 0.000%

    No Known Activations