© 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. 43655
    Prev
    Next
    INDEX
    Explanations

    terms related to complex thinking

    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
    0:0.16
    1:0.03
    2:0.09
    3:0.10
    4:0.09
    5:0.04
    6:0.02
    7:0.01
    8:0.11
    9:0.12
    10:0.08
    11:0.11
    Negative Logits
    usional
    -1.66
    ilts
    -1.49
    Ire
    -1.48
     guiActiveUn
    -1.45
    ensional
    -1.45
    monary
    -1.44
    gyn
    -1.38
    inventoryQuantity
    -1.34
    REF
    -1.30
    terday
    -1.30
    POSITIVE LOGITS
    hof
    1.39
    lington
    1.32
     UD
    1.30
    iasis
    1.30
    ppa
    1.27
     ZIP
    1.27
    ell
    1.26
    oret
    1.26
    eware
    1.23
    alli
    1.23
    Activations Density 0.009%

    No Known Activations