© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6603
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparative relationships and quantities

    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
    0:0.04
    1:0.40
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.08
    7:0.05
    8:0.03
    9:0.11
    10:0.03
    11:0.04
    Negative Logits
    catentry
    -2.89
    tera
    -2.73
    answered
    -2.66
    Scope
    -2.65
    ◼
    -2.62
    ‎
    -2.54
    �
    -2.53
    Spec
    -2.52
    �
    -2.42
    enson
    -2.41
    POSITIVE LOGITS
     half
    6.62
    half
    6.43
    Half
    5.99
     halves
    5.66
     Half
    5.55
     HAL
    4.12
     halfway
    3.92
    thirds
    3.73
     quarter
    3.66
     twice
    3.46
    Activations Density 0.015%

    No Known Activations