© 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. 22100
    Prev
    Next
    INDEX
    Explanations

    instances of the word "is."

    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
    0:0.09
    1:0.07
    2:0.09
    3:0.09
    4:0.04
    5:0.09
    6:0.10
    7:0.04
    8:0.08
    9:0.10
    10:0.12
    11:0.04
    Negative Logits
     drown
    -1.30
    blers
    -1.29
    xff
    -1.26
    xes
    -1.24
    cks
    -1.23
     turbines
    -1.20
    �
    -1.19
    alions
    -1.19
    inces
    -1.18
    phony
    -1.18
    POSITIVE LOGITS
     ende
    2.05
     behav
    1.80
     arrang
    1.51
     streng
    1.50
     awa
    1.49
    endars
    1.48
    ���
    1.45
     warr
    1.45
    endum
    1.44
     terminology
    1.37
    Activations Density 0.000%

    No Known Activations