© 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. 21260
    Prev
    Next
    INDEX
    Explanations

    features related to mouse functionality and performance

    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
    0:0.27
    1:0.03
    2:0.13
    3:0.07
    4:0.05
    5:0.06
    6:0.08
    7:0.05
    8:0.07
    9:0.07
    10:0.05
    11:0.02
    Negative Logits
    externalActionCode
    -3.46
     Renew
    -3.25
     Burnett
    -3.08
    isodes
    -2.91
     Flavoring
    -2.90
     Tara
    -2.78
     renewal
    -2.71
    CBS
    -2.62
    CAST
    -2.61
     episodes
    -2.60
    POSITIVE LOGITS
     mouse
    6.09
    Mouse
    6.03
     Razer
    5.86
    mouse
    5.63
     Mouse
    5.62
     mice
    4.96
     rodent
    3.90
     rodents
    3.59
     erg
    3.53
    Gam
    3.48
    Activations Density 0.007%

    No Known Activations