© 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. 42303
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sense" in various contexts

    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
    0:0.03
    1:0.01
    2:0.22
    3:0.09
    4:0.08
    5:0.05
    6:0.13
    7:0.06
    8:0.05
    9:0.06
    10:0.10
    11:0.06
    Negative Logits
    ngth
    -2.04
    ibaba
    -1.87
    usalem
    -1.75
    ��
    -1.75
    sembly
    -1.71
    semble
    -1.63
    rozen
    -1.60
    apons
    -1.55
    mini
    -1.55
    achelor
    -1.53
    POSITIVE LOGITS
     moot
    1.55
     cliché
    1.55
     implication
    1.54
     misunderstanding
    1.52
     coincidence
    1.50
     presupp
    1.50
     logically
    1.49
     misconception
    1.45
     motiv
    1.43
     assumption
    1.43
    Activations Density 0.003%

    No Known Activations