© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 1251
    Prev
    Next
    INDEX
    Explanations

    sentences discussing biological processes and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.04
    1:0.02
    2:0.05
    3:0.09
    4:0.06
    5:0.12
    6:0.02
    7:0.04
    8:0.04
    9:0.16
    10:0.18
    11:0.13
    Negative Logits
    verty
    -1.21
    adra
    -1.14
     horizont
    -1.12
    enery
    -1.08
    ircraft
    -1.05
    selage
    -1.03
    anship
    -1.02
    chwitz
    -1.01
    pod
    -0.98
    lance
    -0.97
    POSITIVE LOGITS
     correlated
    1.44
     predictive
    1.35
     susceptibility
    1.35
     negatively
    1.30
     detrimental
    1.28
     biomark
    1.26
     predicted
    1.26
     correlations
    1.20
     factors
    1.20
     caus
    1.17
    Activations Density 0.484%

    No Known Activations