© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 400
    Prev
    Next
    INDEX
    Explanations

    references to writing improvement and techniques

    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
    0:0.37
    1:0.02
    2:0.14
    3:0.09
    4:0.02
    5:0.08
    6:0.03
    7:0.04
    8:0.04
    9:0.05
    10:0.03
    11:0.03
    Negative Logits
     Chaff
    -2.96
     CCTV
    -2.87
    ramid
    -2.62
    wcsstore
    -2.58
    ��
    -2.55
     Mub
    -2.51
    aband
    -2.51
    chwitz
    -2.50
    ndum
    -2.44
    lyak
    -2.41
    POSITIVE LOGITS
     writing
    6.29
     writers
    6.17
     Writers
    5.87
    writing
    5.82
    Writ
    5.74
     Writing
    5.70
     literary
    5.66
     writer
    5.66
    Writing
    5.59
     manuscript
    5.50
    Activations Density 0.675%

    No Known Activations