© 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. 12674
    Prev
    Next
    INDEX
    Explanations

    prepositions and verbs related to the continuation of actions

    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
    1:0.04
    2:0.31
    3:0.06
    4:0.04
    5:0.12
    6:0.04
    7:0.02
    8:0.06
    9:0.09
    10:0.07
    11:0.02
    Negative Logits
    Pir
    -1.36
    natureconservancy
    -1.29
    SK
    -1.26
    cest
    -1.24
    kered
    -1.23
     Grizz
    -1.21
     Chiefs
    -1.20
     Rebels
    -1.19
    BUG
    -1.18
    mod
    -1.15
    POSITIVE LOGITS
     onwards
    2.02
    outer
    1.60
     standpoint
    1.53
    oln
    1.49
    ennes
    1.46
    lems
    1.42
    retty
    1.41
    lished
    1.41
     onward
    1.40
    ーク
    1.40
    Activations Density 0.081%

    No Known Activations