© 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. 43463
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a minimum or baseline requirement

    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
    0:0.04
    1:0.02
    2:0.19
    3:0.15
    4:0.12
    5:0.03
    6:0.05
    7:0.04
    8:0.04
    9:0.07
    10:0.12
    11:0.09
    Negative Logits
    cfg
    -1.89
    inventoryQuantity
    -1.73
    etheless
    -1.72
    龍契士
    -1.65
    gger
    -1.53
     Haram
    -1.51
    gered
    -1.48
     induced
    -1.43
    mare
    -1.42
    使
    -1.38
    POSITIVE LOGITS
     Featured
    1.73
     subscriptions
    1.56
     CLICK
    1.41
     subscription
    1.37
     subtitles
    1.35
     sake
    1.34
    opsis
    1.34
     occasional
    1.34
    raits
    1.33
     clarity
    1.32
    Activations Density 0.000%

    No Known Activations