© 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. 43338
    Prev
    Next
    INDEX
    Explanations

    phrases and words regarding origins and historical 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
    0:0.01
    1:0.01
    2:0.09
    3:0.05
    4:0.13
    5:0.02
    6:0.06
    7:0.36
    8:0.02
    9:0.02
    10:0.09
    11:0.09
    Negative Logits
    phies
    -1.90
    aptic
    -1.65
    iatric
    -1.62
    luent
    -1.58
    erning
    -1.53
    iatrics
    -1.50
    ooth
    -1.49
    urances
    -1.49
    edient
    -1.43
    yss
    -1.42
    POSITIVE LOGITS
     genesis
    1.72
     origins
    1.47
     myth
    1.43
     rumor
    1.39
     causation
    1.37
     myths
    1.36
     fragment
    1.33
     miscon
    1.32
     diver
    1.30
     strand
    1.29
    Activations Density 0.009%

    No Known Activations