© 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. 4669
    Prev
    Next
    INDEX
    Explanations

    repeated symbols or special characters

    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
    1:0.03
    2:0.03
    3:0.09
    4:0.05
    5:0.12
    6:0.05
    7:0.04
    8:0.07
    9:0.02
    10:0.08
    11:0.33
    Negative Logits
    Advertisement
    -5.43
    ,...
    -4.78
    }}}
    -4.40
     ''
    -4.38
    ,)
    -4.31
    .--
    -4.30
     ‎
    -4.22
    Newsletter
    -3.97
    ''
    -3.89
    .''
    -3.87
    POSITIVE LOGITS
     –
    8.23
     Nato
    4.50
     ­
    4.17
     (£
    4.10
     Nasa
    3.96
     Isis
    3.92
     behavioural
    3.90
     US
    3.78
    –
    3.76
     >
    3.67
    Activations Density 0.048%

    No Known Activations