© 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. 9-ATT-KK
    11. 14594
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "said" and related reporting verbs in the context of statements or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.16
    2:0.05
    3:0.05
    4:0.06
    5:0.07
    6:0.04
    7:0.05
    8:0.05
    9:0.24
    10:0.10
    11:0.02
    Negative Logits
    BIP
    -3.23
    xual
    -3.21
    uer
    -2.88
    ueless
    -2.84
    vir
    -2.83
     Frie
    -2.54
    idan
    -2.51
     FACE
    -2.46
     poster
    -2.44
    buf
    -2.42
    POSITIVE LOGITS
    ando
    2.92
     Ta
    2.76
    commerce
    2.66
    atsu
    2.64
    arr
    2.62
    aza
    2.58
     Walton
    2.55
    Tang
    2.55
     Ord
    2.53
    quickShipAvailable
    2.52
    Activations Density 0.002%

    No Known Activations