© 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. 12212
    Prev
    Next
    INDEX
    Explanations

    mentions of potentially hazardous or sensitive matters

    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
    0:0.07
    1:0.02
    2:0.07
    3:0.09
    4:0.03
    5:0.14
    6:0.05
    7:0.06
    8:0.15
    9:0.07
    10:0.13
    11:0.06
    Negative Logits
    iky
    -1.41
    imar
    -1.36
    ité
    -1.33
    .).
    -1.29
    アル
    -1.27
    quished
    -1.27
    ipel
    -1.24
    illion
    -1.24
     Helpful
    -1.24
    ilet
    -1.22
    POSITIVE LOGITS
     relies
    1.27
     shouldn
    1.24
     lacks
    1.20
     hadn
    1.19
     had
    1.18
     indeed
    1.18
     intends
    1.17
    should
    1.15
     should
    1.13
     cannot
    1.13
    Activations Density 0.394%

    No Known Activations