© 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. 15065
    Prev
    Next
    INDEX
    Explanations

    instances of words related to transformation or change

    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
    0:0.11
    1:0.04
    2:0.06
    3:0.06
    4:0.09
    5:0.09
    6:0.05
    7:0.09
    8:0.07
    9:0.03
    10:0.16
    11:0.09
    Negative Logits
    etheless
    -1.62
    conom
    -1.22
     listened
    -1.07
     alluded
    -1.06
    terday
    -1.00
    ️
    -0.97
     penchant
    -0.96
     UNCLASSIFIED
    -0.94
     declined
    -0.93
     temperament
    -0.92
    POSITIVE LOGITS
    livion
    1.41
     Osc
    1.07
     exhaustion
    1.00
    schild
    0.95
    ixel
    0.92
     Hole
    0.91
    FIELD
    0.91
     adulthood
    0.87
    irth
    0.87
     Ply
    0.87
    Activations Density 0.069%

    No Known Activations