© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3233
    Prev
    Next
    INDEX
    Explanations

    references to local government or organizational actions

    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
    0:0.06
    1:0.03
    2:0.06
    3:0.03
    4:0.05
    5:0.03
    6:0.24
    7:0.05
    8:0.07
    9:0.27
    10:0.02
    11:0.04
    Negative Logits
    Carter
    -3.90
     Daisy
    -3.77
     Carter
    -3.63
    sky
    -3.62
     Shia
    -3.62
     Feldman
    -3.48
     Houth
    -3.48
     celeb
    -3.45
     lightsaber
    -3.44
     Scar
    -3.41
    POSITIVE LOGITS
    Portland
    9.59
     Portland
    9.23
     Oregon
    7.66
    Oregon
    7.35
     Blazers
    6.04
     Eugene
    5.91
     Timbers
    5.86
     Salem
    4.75
    PORT
    4.74
     Providence
    4.56
    Activations Density 0.007%

    No Known Activations