© 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. 20256
    Prev
    Next
    INDEX
    Explanations

    components and coding patterns in Angular

    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
    0:0.10
    1:0.02
    2:0.07
    3:0.06
    4:0.03
    5:0.09
    6:0.09
    7:0.04
    8:0.30
    9:0.09
    10:0.03
    11:0.03
    Negative Logits
     Antarctic
    -4.20
    ocaust
    -3.95
     Antarctica
    -3.85
     Falk
    -3.67
    bil
    -3.51
     Penguins
    -3.50
    Meg
    -3.44
     Zimbabwe
    -3.43
     Dahl
    -3.38
    usalem
    -3.36
    POSITIVE LOGITS
     Angular
    7.44
    angular
    6.46
     ng
    6.16
     angular
    5.46
     Ng
    5.01
     Ember
    4.91
    Ang
    4.19
    JS
    4.05
    .$
    4.01
     jQuery
    3.88
    Activations Density 0.010%

    No Known Activations