© 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. 3015
    Prev
    Next
    INDEX
    Explanations

    descriptions or evaluations of visual elements, particularly related to graffiti and political expressions

    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
    0:0.17
    1:0.02
    2:0.26
    3:0.07
    4:0.05
    5:0.07
    6:0.06
    7:0.06
    8:0.07
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
    imester
    -3.59
    ajor
    -3.14
    compan
    -3.08
    regnancy
    -3.00
    ellen
    -2.92
    ptin
    -2.80
    adh
    -2.80
    atonin
    -2.78
    nutrition
    -2.77
    Flight
    -2.76
    POSITIVE LOGITS
     vandalism
    7.00
     vandal
    6.79
     graffiti
    6.40
     swast
    4.82
     mural
    4.37
    andals
    4.28
     spray
    4.27
     arson
    4.25
    ffiti
    4.01
     mischief
    3.53
    Activations Density 0.020%

    No Known Activations