© 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. 2-ATT-KK
    11. 21439
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional sentiments or reflections on experiences

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.03
    1:0.06
    2:0.07
    3:0.08
    4:0.09
    5:0.13
    6:0.09
    7:0.04
    8:0.09
    9:0.18
    10:0.06
    11:0.04
    Negative Logits
    conservancy
    -1.50
    etheless
    -1.45
    partial
    -1.26
    immers
    -1.24
     briefly
    -1.21
     conver
    -1.15
    emetery
    -1.13
    utterstock
    -1.11
    allery
    -1.10
     intern
    -1.07
    POSITIVE LOGITS
    Reply
    1.37
    Agent
    1.35
    Russ
    1.23
    "...
    1.21
    "]=>
    1.20
    POR
    1.19
     nails
    1.18
    Vers
    1.18
    DH
    1.17
    Forward
    1.16
    Activations Density 0.057%

    No Known Activations