© 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. 9-ATT-KK
    11. 7804
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of positive and negative evaluations

    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
    1:0.03
    2:0.11
    3:0.05
    4:0.03
    5:0.04
    6:0.24
    7:0.03
    8:0.03
    9:0.22
    10:0.04
    11:0.03
    Negative Logits
     Seraph
    -4.69
     Johannes
    -3.94
    Scar
    -3.66
     MAP
    -3.52
     Sector
    -3.51
     Mei
    -3.48
     Meg
    -3.42
    ��
    -3.38
     Reyn
    -3.38
     Leah
    -3.36
    POSITIVE LOGITS
    Throw
    7.29
     throw
    6.98
    throw
    6.95
     Throw
    6.53
     throwing
    6.52
     thrown
    6.49
     throws
    6.42
     threw
    5.91
     hurled
    5.21
     toss
    5.21
    Activations Density 0.006%

    No Known Activations