© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-ATT-KK
    11. 14390
    Prev
    Next
    INDEX
    Explanations

    specific instances of caution or warnings in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.07
    8:0.09
    9:0.08
    10:0.07
    11:0.06
    Negative Logits
    edded
    -3.19
    odox
    -3.04
    footed
    -2.95
    retty
    -2.79
    izabeth
    -2.79
    ciating
    -2.72
    culosis
    -2.69
    oubted
    -2.65
    edged
    -2.64
    avid
    -2.64
    POSITIVE LOGITS
     Nar
    2.86
     Claus
    2.83
    �
    2.80
     Buddh
    2.76
    �
    2.71
    Nar
    2.70
     Nur
    2.66
    particip
    2.60
     hog
    2.59
     Machina
    2.55
    Activations Density 0.000%

    No Known Activations