© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 777
    Prev
    Next
    INDEX
    Explanations

    the preposition "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.21
    2:0.03
    3:0.11
    4:0.02
    5:0.05
    6:0.11
    7:0.05
    8:0.02
    9:0.13
    10:0.15
    11:0.03
    Negative Logits
    gans
    -2.80
     Panc
    -2.50
     Pil
    -2.46
    IFIED
    -2.46
    ribed
    -2.45
    GH
    -2.43
    IFA
    -2.42
     Phelps
    -2.40
    Fed
    -2.38
    iliated
    -2.37
    POSITIVE LOGITS
     Tome
    3.01
     morale
    2.81
     [&
    2.73
     bookmark
    2.64
    etime
    2.59
     enchant
    2.47
    time
    2.46
     loudspe
    2.45
     simultane
    2.44
    jar
    2.41
    Activations Density 0.001%

    No Known Activations