© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 10586
    Prev
    Next
    INDEX
    Explanations

    phrases related to sharing or emailing content to friends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.01
    2:0.03
    3:0.06
    4:0.36
    5:0.06
    6:0.03
    7:0.04
    8:0.17
    9:0.07
    10:0.05
    11:0.03
    Negative Logits
    }}}
    -4.27
    )}
    -3.75
    },{"
    -2.78
     },
    -2.77
    hooting
    -2.66
    ]}
    -2.64
    }\
    -2.60
    �
    -2.54
    ィ
    -2.41
    �
    -2.40
    POSITIVE LOGITS
     [-
    2.15
            
    2.08
    hemer
    2.06
     quer
    2.01
     Verb
    1.95
    osite
    1.93
       
    1.93
     apiece
    1.93
    ':
    1.91
     cryptic
    1.87
    Activations Density 0.002%

    No Known Activations