© 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. 10196
    Prev
    Next
    INDEX
    Explanations

    phrases related to color symbolism and its association with cultural figures or identities

    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
    0:0.09
    1:0.02
    2:0.06
    3:0.04
    4:0.04
    5:0.04
    6:0.30
    7:0.02
    8:0.04
    9:0.23
    10:0.02
    11:0.03
    Negative Logits
     Yor
    -4.17
     Adin
    -4.13
    Rod
    -4.02
     Perl
    -3.98
    zsche
    -3.98
     Tommy
    -3.92
     Trin
    -3.87
     Fischer
    -3.83
     Rodney
    -3.81
    ischer
    -3.80
    POSITIVE LOGITS
     Cloud
    10.43
    Cloud
    9.91
    cloud
    9.69
     cloud
    9.56
     Clouds
    9.01
     clouds
    8.93
     cloudy
    5.57
     AWS
    5.00
    storms
    4.56
     Azure
    4.47
    Activations Density 0.006%

    No Known Activations