© 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. 3-ATT-KK
    11. 9588
    Prev
    Next
    INDEX
    Explanations

    conditional verbs that imply hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.03
    2:0.07
    3:0.03
    4:0.02
    5:0.08
    6:0.06
    7:0.04
    8:0.15
    9:0.15
    10:0.14
    11:0.07
    Negative Logits
    interstitial
    -1.31
    assemb
    -0.98
    assembly
    -0.97
     (>
    -0.97
    -,
    -0.94
    tainment
    -0.93
    osis
    -0.92
    oct
    -0.90
    ynamic
    -0.89
     assembly
    -0.88
    POSITIVE LOGITS
    swer
    1.35
     retaliate
    1.34
     waive
    1.18
     suffice
    1.13
     reciproc
    1.08
    ratom
    1.04
     nominate
    1.03
    ede
    1.01
     prevail
    0.99
    eway
    0.99
    Activations Density 0.190%

    No Known Activations