© 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 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. 13320
    Prev
    Next
    INDEX
    Explanations

    instances of citations or references in a discussion

    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
    0:0.14
    1:0.02
    2:0.09
    3:0.23
    4:0.02
    5:0.07
    6:0.02
    7:0.08
    8:0.07
    9:0.02
    10:0.05
    11:0.14
    Negative Logits
     flavours
    -2.99
     colours
    -2.87
     equivalents
    -2.61
     practise
    -2.61
     splend
    -2.59
     favourites
    -2.57
     recognise
    -2.56
     resemb
    -2.55
     fulfil
    -2.48
     rumours
    -2.47
    POSITIVE LOGITS
    �
    3.38
    Secretary
    3.08
    director
    3.02
    Ohio
    2.96
    Department
    2.89
    Director
    2.89
    ​​
    2.88
    Smith
    2.82
    President
    2.82
    Executive
    2.81
    Activations Density 0.099%

    No Known Activations