© 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. 15446
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate frequency or emphasis in activities or statements

    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
    0:0.04
    1:0.03
    2:0.05
    3:0.16
    4:0.03
    5:0.05
    6:0.03
    7:0.04
    8:0.05
    9:0.03
    10:0.42
    11:0.03
    Negative Logits
     underwent
    -2.25
     incorporates
    -2.19
     prepares
    -2.10
     may
    -2.09
     creates
    -2.05
    atari
    -2.04
     resides
    -2.03
     might
    -1.98
    alsa
    -1.96
     approaches
    -1.91
    POSITIVE LOGITS
     EVER
    3.11
     anymore
    3.01
     slightest
    2.72
     :(
    2.62
     foreseeable
    2.57
     whatsoever
    2.51
    yet
    2.35
    "]=>
    2.33
     ANY
    2.32
     Enough
    2.32
    Activations Density 0.010%

    No Known Activations