© 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. 13358
    Prev
    Next
    INDEX
    Explanations

    terms related to data and statistics from reports and records

    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
    0:0.02
    1:0.02
    2:0.03
    3:0.04
    4:0.09
    5:0.20
    6:0.03
    7:0.04
    8:0.01
    9:0.41
    10:0.01
    11:0.04
    Negative Logits
    atra
    -2.85
    Joined
    -2.53
    Introduced
    -2.50
    joined
    -2.49
    pires
    -2.45
     joined
    -2.44
    emis
    -2.42
     waged
    -2.38
     embarked
    -2.36
    dinand
    -2.32
    POSITIVE LOGITS
     indicate
    4.98
     suggest
    4.38
     suggesting
    4.22
     indicating
    4.13
    suggest
    4.05
     imply
    4.05
     hint
    3.92
     underestimate
    3.87
     refute
    3.80
     suggests
    3.71
    Activations Density 0.328%

    No Known Activations