© 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. 22604
    Prev
    Next
    INDEX
    Explanations

    numerical values related to performance statistics

    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
    0:0.05
    1:0.07
    2:0.03
    3:0.06
    4:0.12
    5:0.25
    6:0.04
    7:0.04
    8:0.05
    9:0.05
    10:0.03
    11:0.16
    Negative Logits
     pse
    -2.48
     loser
    -2.43
    �
    -2.42
     princ
    -2.35
     victories
    -2.35
    forth
    -2.33
     Winning
    -2.31
     TDs
    -2.30
     gobl
    -2.29
     defeats
    -2.27
    POSITIVE LOGITS
     Required
    2.60
    egu
    2.56
    Materials
    2.43
    itect
    2.43
    iox
    2.34
     reservoir
    2.29
    ermanent
    2.23
    illance
    2.21
    scope
    2.20
     Pav
    2.19
    Activations Density 0.000%

    No Known Activations