© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22042
    Prev
    Next
    INDEX
    Explanations

    patterns of specific conjunctions and qualifiers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.14
    3:0.10
    4:0.11
    5:0.10
    6:0.04
    7:0.06
    8:0.09
    9:0.06
    10:0.11
    11:0.06
    Negative Logits
    itutes
    -1.11
    atives
    -1.03
    itution
    -1.00
    arettes
    -0.99
    lled
    -0.99
    Charges
    -0.99
    arez
    -0.98
    Kill
    -0.98
    zag
    -0.95
     Expend
    -0.92
    POSITIVE LOGITS
     nonetheless
    1.44
    etheless
    1.36
     persisted
    1.36
     conclud
    1.34
     importantly
    1.29
     nevertheless
    1.27
     acknow
    1.25
     alas
    1.24
     beware
    1.24
     prevailed
    1.22
    Activations Density 0.090%

    No Known Activations