© 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. 9-ATT-KK
    6. 19687
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in the film industry and their associated roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.06
    3:0.07
    4:0.03
    5:0.04
    6:0.07
    7:0.06
    8:0.43
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
     Charlotte
    -3.91
     Kaw
    -3.48
     Richmond
    -3.45
     Raleigh
    -3.43
     Oakland
    -3.42
    AMI
    -3.40
     Charleston
    -3.40
    Miami
    -3.36
    NBA
    -3.34
     Durham
    -3.31
    POSITIVE LOGITS
     Hungarian
    9.20
     Budapest
    8.86
     Hungary
    8.67
    Hung
    7.54
     Hung
    7.00
     Sz
    6.40
     Slovakia
    6.39
     Slov
    6.29
     Sloven
    6.00
     Viktor
    5.84
    Activations Density 0.009%

    No Known Activations