© 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. 995
    Prev
    Next
    INDEX
    Explanations

    instances of negation and their context within the text

    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
    1:0.05
    2:0.07
    3:0.10
    4:0.03
    5:0.05
    6:0.18
    7:0.04
    8:0.03
    9:0.19
    10:0.04
    11:0.05
    Negative Logits
     Mines
    -3.75
     Pigs
    -3.46
     Wink
    -3.41
     mig
    -3.23
     Piet
    -3.21
     Mik
    -3.12
     Pig
    -3.09
     synagogue
    -3.06
     Plant
    -3.05
     Vet
    -3.04
    POSITIVE LOGITS
    Length
    5.45
     Length
    5.04
    length
    4.77
     length
    4.51
    Filename
    3.96
    filename
    3.93
    orth
    3.77
     lengths
    3.64
    ngth
    3.44
    lear
    3.21
    Activations Density 0.000%

    No Known Activations