© 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. 19458
    Prev
    Next
    INDEX
    Explanations

    phrases that relate to storytelling and absurd or humorous elements

    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
    0:0.06
    1:0.03
    2:0.06
    3:0.04
    4:0.04
    5:0.03
    6:0.32
    7:0.04
    8:0.06
    9:0.23
    10:0.02
    11:0.03
    Negative Logits
    ricks
    -4.05
    "]=>
    -3.79
    MSN
    -3.72
     Kinect
    -3.72
    tile
    -3.63
     ESC
    -3.61
    Jess
    -3.58
    Interstitial
    -3.57
     Adelaide
    -3.53
     Jess
    -3.45
    POSITIVE LOGITS
     Bear
    10.15
    Bear
    9.44
     bear
    9.22
     bears
    8.50
     Bears
    8.46
    bear
    8.20
     grizz
    6.57
     Grizz
    6.37
     Bore
    5.78
     bearing
    5.22
    Activations Density 0.010%

    No Known Activations