© 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. 3-ATT-KK
    11. 11008
    Prev
    Next
    INDEX
    Explanations

    phrases indicating official statements or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.09
    2:0.07
    3:0.02
    4:0.18
    5:0.14
    6:0.06
    7:0.06
    8:0.08
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
     northeastern
    -1.44
    anwhile
    -1.41
     Airl
    -1.40
     radios
    -1.33
     descendant
    -1.32
    rosis
    -1.31
     courthouse
    -1.31
     rebuilt
    -1.30
     conver
    -1.28
     merged
    -1.27
    POSITIVE LOGITS
    Coun
    1.58
    '"
    1.56
     [+
    1.55
    Response
    1.53
     offence
    1.52
    Reply
    1.50
     Miliband
    1.45
    Labour
    1.44
    Desc
    1.44
    "'
    1.43
    Activations Density 0.059%

    No Known Activations