© 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. 22161
    Prev
    Next
    INDEX
    Explanations

    references to love and affection towards people

    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
    0:0.06
    1:0.01
    2:0.22
    3:0.06
    4:0.05
    5:0.07
    6:0.01
    7:0.04
    8:0.18
    9:0.12
    10:0.07
    11:0.04
    Negative Logits
    ��
    -1.45
    ocument
    -1.26
    owned
    -1.25
    accessible
    -1.24
    uler
    -1.19
    hari
    -1.16
    ailable
    -1.16
    galitarian
    -1.16
     wiser
    -1.14
    aye
    -1.13
    POSITIVE LOGITS
    ゼ
    1.14
    STD
    1.08
     ART
    1.07
    agnetic
    1.05
     brakes
    1.05
    ドラゴン
    1.04
    atre
    1.04
    TEXTURE
    1.04
     shaving
    1.04
     metaphors
    1.03
    Activations Density 0.025%

    No Known Activations