© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 4405
    Prev
    Next
    INDEX
    Explanations

    words related to interactions and discussions in various contexts

    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
    0:0.06
    1:0.11
    2:0.10
    3:0.05
    4:0.04
    5:0.03
    6:0.15
    7:0.03
    8:0.04
    9:0.30
    10:0.02
    11:0.02
    Negative Logits
     Muller
    -3.97
    asma
    -3.83
     Hicks
    -3.26
    Magn
    -3.23
     mur
    -3.21
    mus
    -3.15
     Rutherford
    -3.11
    uls
    -3.05
     Loud
    -2.99
    cffffcc
    -2.99
    POSITIVE LOGITS
     End
    5.58
     Ending
    5.29
     END
    5.14
    END
    4.91
    end
    4.86
     Ends
    4.80
    End
    4.72
     endings
    4.59
     endpoint
    4.49
     ende
    4.46
    Activations Density 0.008%

    No Known Activations