© 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. 15443
    Prev
    Next
    INDEX
    Explanations

    phrases consisting of the word "and" combined with verbs related to repetition or continuation

    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
    0:0.03
    1:0.47
    2:0.03
    3:0.06
    4:0.03
    5:0.03
    6:0.04
    7:0.08
    8:0.03
    9:0.07
    10:0.05
    11:0.03
    Negative Logits
    ahime
    -2.38
     earliest
    -2.35
    minimum
    -2.33
     minimizing
    -2.28
    *)
    -2.26
     closest
    -2.25
    idis
    -2.25
     antid
    -2.24
     widest
    -2.23
    zn
    -2.19
    POSITIVE LOGITS
     again
    7.46
    again
    7.01
     Again
    6.50
    Again
    5.31
    Finally
    4.54
     AGA
    4.52
     anymore
    4.38
    another
    4.32
     anew
    4.13
    Lastly
    4.12
    Activations Density 0.016%

    No Known Activations