© 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. 3224
    Prev
    Next
    INDEX
    Explanations

    references to visual elements and contrasting themes in a narrative context

    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
    0:0.03
    1:0.02
    2:0.08
    3:0.06
    4:0.10
    5:0.05
    6:0.29
    7:0.06
    8:0.07
    9:0.07
    10:0.05
    11:0.08
    Negative Logits
     sorely
    -1.25
    cair
    -1.25
     Xer
    -1.17
    wolves
    -1.15
     secondly
    -1.10
     gladly
    -1.09
     Ender
    -1.05
     relentlessly
    -1.05
     Bers
    -1.04
     catching
    -1.03
    POSITIVE LOGITS
    ゴン
    1.47
    ODUCT
    1.46
    vironment
    1.37
    istant
    1.35
    ample
    1.31
    abyte
    1.30
    ctive
    1.29
    20439
    1.29
    ophysical
    1.27
    istance
    1.25
    Activations Density 0.050%

    No Known Activations