© 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. 2-ATT-KK
    11. 22053
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs expressing varying degrees of intensity or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.04
    2:0.07
    3:0.15
    4:0.07
    5:0.10
    6:0.03
    7:0.07
    8:0.05
    9:0.06
    10:0.13
    11:0.06
    Negative Logits
     Kessler
    -0.97
     Pandora
    -0.82
    プ
    -0.81
     spray
    -0.80
     Insight
    -0.79
     Wong
    -0.78
     Invisible
    -0.78
     clipping
    -0.78
     IRC
    -0.77
     Cir
    -0.77
    POSITIVE LOGITS
    atto
    1.14
    iga
    1.07
    auld
    0.99
    athed
    0.96
    nered
    0.94
    mercial
    0.94
    VALUE
    0.93
    mented
    0.93
    xual
    0.92
    igan
    0.92
    Activations Density 0.142%

    No Known Activations