© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20780
    Prev
    Next
    INDEX
    Explanations

    sentences that question or critique actions or statements made by Donald Trump

    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
    0:0.10
    1:0.03
    2:0.08
    3:0.05
    4:0.04
    5:0.03
    6:0.19
    7:0.08
    8:0.09
    9:0.19
    10:0.04
    11:0.04
    Negative Logits
     CAD
    -3.78
     MAS
    -3.75
    osaurs
    -3.56
     Osaka
    -3.50
     mer
    -3.42
     Singapore
    -3.42
     Mats
    -3.41
     MAP
    -3.40
     homosexual
    -3.37
     Mü
    -3.32
    POSITIVE LOGITS
     Fallon
    10.41
     Harrington
    6.97
    Fall
    5.81
     Fitzpatrick
    4.36
     Rollins
    4.11
     Kimmel
    4.07
     Ingram
    3.98
     Burton
    3.97
     Gallagher
    3.92
     Fallout
    3.92
    Activations Density 0.003%

    No Known Activations