© 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. 2-ATT-KK
    6. 23377
    Prev
    Next
    INDEX
    Explanations

    newsletters and subscription-related information from The New York Times

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.09
    1:0.07
    2:0.10
    3:0.08
    4:0.06
    5:0.06
    6:0.09
    7:0.06
    8:0.13
    9:0.10
    10:0.09
    11:0.03
    Negative Logits
     GB
    -1.42
     TB
    -1.39
     Firstly
    -1.39
     <-
    -1.37
    ケ
    -1.36
    ovember
    -1.33
    tein
    -1.28
     BT
    -1.20
     upfront
    -1.17
    gart
    -1.16
    POSITIVE LOGITS
    ."[
    1.49
    axies
    1.46
    bryce
    1.41
    �醒
    1.41
    )].
    1.40
     wreckage
    1.33
    ��
    1.33
    ]."
    1.30
     Zup
    1.27
    ��
    1.27
    Activations Density 0.002%

    No Known Activations