© 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. 9305
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and periods, indicating breaks in thought or structure within the text

    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
    0:0.05
    1:0.04
    2:0.02
    3:0.05
    4:0.11
    5:0.04
    6:0.04
    7:0.05
    8:0.03
    9:0.04
    10:0.03
    11:0.45
    Negative Logits
     racer
    -2.21
    ****
    -2.18
     quir
    -2.14
     rave
    -2.05
     disco
    -2.01
     crown
    -1.98
     seeker
    -1.97
     goodness
    -1.97
    *****
    -1.96
     squash
    -1.94
    POSITIVE LOGITS
    ,
    6.22
    ,"
    5.41
    ,,
    5.36
    ,,,,
    4.89
     ),
    4.87
    .)
    4.59
     )
    4.51
     ;
    4.32
    ?,
    4.24
     );
    4.11
    Activations Density 0.277%

    No Known Activations