© 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. 5-ATT-KK
    11. 18480
    Prev
    Next
    INDEX
    Explanations

    instances of the word "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 @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.07
    3:0.08
    4:0.08
    5:0.04
    6:0.26
    7:0.04
    8:0.11
    9:0.08
    10:0.06
    11:0.08
    Negative Logits
     Runtime
    -1.42
     Choice
    -1.36
    Choice
    -1.33
     Scand
    -1.27
    Scope
    -1.26
    STD
    -1.23
     PID
    -1.21
    Spoiler
    -1.20
    tm
    -1.20
     Reilly
    -1.18
    POSITIVE LOGITS
     mosqu
    1.59
    tackle
    1.46
    insula
    1.34
    iggurat
    1.31
    enei
    1.30
     Taj
    1.30
    essment
    1.29
    rison
    1.24
     frequ
    1.22
    usp
    1.20
    Activations Density 0.003%

    No Known Activations