© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 336
    Prev
    Next
    INDEX
    Explanations

    phrases indicating problems or challenges 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
    0:0.05
    1:0.02
    2:0.08
    3:0.45
    4:0.03
    5:0.07
    6:0.02
    7:0.05
    8:0.03
    9:0.01
    10:0.12
    11:0.02
    Negative Logits
     united
    -2.52
    Peace
    -2.51
    united
    -2.42
     Nobel
    -2.35
     Emmanuel
    -2.34
     Liberation
    -2.29
     �
    -2.16
     Peace
    -2.13
    �
    -2.13
    Together
    -2.13
    POSITIVE LOGITS
     cumbers
    4.04
     annoying
    3.72
     sloppy
    3.70
     distractions
    3.65
     clutter
    3.62
     glitches
    3.52
     awkward
    3.51
     tedious
    3.50
     delays
    3.48
     confusion
    3.43
    Activations Density 1.525%

    No Known Activations