© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-ATT-KK
    11. 21314
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial proceedings

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.06
    1:0.03
    2:0.30
    3:0.05
    4:0.03
    5:0.12
    6:0.02
    7:0.03
    8:0.04
    9:0.16
    10:0.07
    11:0.03
    Negative Logits
    aucas
    -1.63
    phalt
    -1.53
    姫
    -1.50
    secut
    -1.50
    gyn
    -1.42
    龍喚士
    -1.39
     holidays
    -1.39
     Oss
    -1.38
     cursing
    -1.37
    ufact
    -1.35
    POSITIVE LOGITS
    naire
    1.71
     HM
    1.47
    tnc
    1.42
     DF
    1.41
    VW
    1.38
    SHIP
    1.38
    MIT
    1.37
     VT
    1.35
     CAM
    1.35
     LR
    1.34
    Activations Density 0.242%

    No Known Activations