© 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. 23306
    Prev
    Next
    INDEX
    Explanations

    data related to various studies, reports, and analyses containing diverse topics such as financial issues, medical conditions, city surveys, AI technologies, and more

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

    phrases related to data collection and its analysis

    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
    1:0.02
    2:0.16
    3:0.03
    4:0.34
    5:0.05
    6:0.02
    7:0.03
    8:0.06
    9:0.16
    10:0.03
    11:0.01
    Negative Logits
    joy
    -1.58
    imar
    -1.43
     distingu
    -1.35
    chlor
    -1.32
    ranged
    -1.31
     jab
    -1.30
     immunity
    -1.26
    Laughs
    -1.22
    ido
    -1.22
    �
    -1.20
    POSITIVE LOGITS
     Analytics
    1.56
    ascript
    1.46
     PLAN
    1.45
    QL
    1.43
    transfer
    1.42
     Nerd
    1.37
    Reviewer
    1.36
    ioxide
    1.35
    riter
    1.34
    ursday
    1.33
    Activations Density 0.029%

    No Known Activations