© 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. 10-ATT-KK
    11. 6831
    Prev
    Next
    INDEX
    Explanations

    elements related to ratings and classifications within community contexts

    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
    0:0.04
    1:0.04
    2:0.40
    3:0.07
    4:0.05
    5:0.03
    6:0.04
    7:0.07
    8:0.03
    9:0.04
    10:0.10
    11:0.04
    Negative Logits
    amsung
    -2.92
    Canada
    -2.90
    �
    -2.85
     �
    -2.81
    iami
    -2.55
    Harris
    -2.52
    Johnson
    -2.52
    tv
    -2.50
    http
    -2.50
    ッ
    -2.38
    POSITIVE LOGITS
     C
    4.93
     B
    4.87
     F
    4.72
     S
    4.62
     D
    4.61
     P
    4.60
     M
    4.51
     T
    4.43
     G
    4.23
     E
    4.17
    Activations Density 0.174%

    No Known Activations