© 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. 9958
    Prev
    Next
    INDEX
    Explanations

    references to objects and their characteristics

    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
    1:0.02
    2:0.03
    3:0.10
    4:0.04
    5:0.04
    6:0.02
    7:0.12
    8:0.03
    9:0.02
    10:0.48
    11:0.01
    Negative Logits
    aucus
    -2.28
    ê
    -2.04
    ortun
    -1.94
    angering
    -1.85
    ��
    -1.84
    initely
    -1.81
    ]=
    -1.81
    gur
    -1.80
    erity
    -1.76
    leaning
    -1.75
    POSITIVE LOGITS
     tropes
    2.26
     }}
    2.22
     alike
    2.15
     anymore
    2.09
     replicated
    2.06
    }}
    1.99
     same
    1.98
     as
    1.97
     everywhere
    1.85
     Same
    1.82
    Activations Density 0.209%

    No Known Activations