© 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. 15703
    Prev
    Next
    INDEX
    Explanations

    criteria and qualifications for applicants in various contexts, especially in educational and programming fields

    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
    0:0.07
    1:0.03
    2:0.06
    3:0.06
    4:0.18
    5:0.10
    6:0.07
    7:0.09
    8:0.04
    9:0.11
    10:0.04
    11:0.08
    Negative Logits
    NetMessage
    -2.93
    ッド
    -2.80
     haun
    -2.73
    toggle
    -2.72
    ヤ
    -2.63
    roo
    -2.59
    Enlarge
    -2.58
     strang
    -2.57
    oiler
    -2.55
     pandemonium
    -2.48
    POSITIVE LOGITS
     satisfactory
    3.22
     proficient
    3.19
     adequate
    3.06
     sufficient
    2.99
     satisf
    2.95
     adequately
    2.90
    Excellent
    2.78
    Requirements
    2.77
     sufficiently
    2.74
     competent
    2.72
    Activations Density 0.005%

    No Known Activations