© 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. 5-ATT-KK
    11. 40674
    Prev
    Next
    INDEX
    Explanations

    phrases related to estimation and numerical evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    2:0.04
    3:0.09
    4:0.17
    5:0.03
    6:0.04
    7:0.25
    8:0.05
    9:0.03
    10:0.10
    11:0.11
    Negative Logits
    icrobial
    -1.50
    container
    -1.43
     rinse
    -1.39
    adies
    -1.37
    ゴン
    -1.35
    udeb
    -1.34
    alogue
    -1.34
    anamo
    -1.30
    feel
    -1.25
    ingo
    -1.25
    POSITIVE LOGITS
    Sequ
    1.28
     sizeof
    1.26
    oen
    1.19
     Rates
    1.18
     Corp
    1.16
     CRC
    1.14
     estimating
    1.13
    CLA
    1.11
     Tav
    1.10
     Vec
    1.10
    Activations Density 0.038%

    No Known Activations