© 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. 10-ATT-KK
    11. 13620
    Prev
    Next
    INDEX
    Explanations

    names of basketball players and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.07
    2:0.22
    3:0.06
    4:0.08
    5:0.06
    6:0.08
    7:0.07
    8:0.06
    9:0.05
    10:0.04
    11:0.05
    Negative Logits
    1920
    -2.80
     arbitration
    -2.78
     tribunal
    -2.65
     compan
    -2.63
    ANG
    -2.50
     1700
    -2.45
     vibration
    -2.45
    ement
    -2.41
     mould
    -2.41
     bottleneck
    -2.41
    POSITIVE LOGITS
     (#
    7.23
    =#
    3.52
    ##
    3.33
     (*
    3.33
    wy
    3.29
    gly
    3.25
    ###
    3.25
     ($)
    3.15
     Olive
    3.13
     Penny
    3.08
    Activations Density 0.001%

    No Known Activations