© 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. 2-ATT-KK
    11. 22553
    Prev
    Next
    INDEX
    Explanations

    topics or keywords related to news and articles, potentially related to crime, politics, or industry

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    topics related to health and wellness issues

    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
    0:0.07
    1:0.04
    2:0.13
    3:0.08
    4:0.22
    5:0.05
    6:0.05
    7:0.03
    8:0.10
    9:0.09
    10:0.06
    11:0.02
    Negative Logits
    tein
    -1.36
    icidal
    -1.26
    lite
    -1.18
    USD
    -1.16
    bley
    -1.15
    athing
    -1.14
    adra
    -1.14
    APTER
    -1.11
    AGES
    -1.10
     cit
    -1.09
    POSITIVE LOGITS
     millenn
    1.56
     Questions
    1.31
    Fact
    1.29
    Shar
    1.24
    iosyncr
    1.21
     unden
    1.20
    cius
    1.20
    anwhile
    1.19
     Diseases
    1.16
     Topic
    1.14
    Activations Density 0.002%

    No Known Activations