© 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. 3220
    Prev
    Next
    INDEX
    Explanations

    elements related to comparisons and contrasts, particularly in the context of public perception and social norms

    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
    3:0.03
    4:0.05
    5:0.02
    6:0.24
    7:0.04
    8:0.09
    9:0.27
    10:0.02
    11:0.02
    Negative Logits
     jog
    -4.08
     Krug
    -4.05
     Rug
    -4.00
     Dog
    -3.85
    gi
    -3.59
     Jinn
    -3.59
     rake
    -3.53
     bags
    -3.50
     yoga
    -3.46
     bag
    -3.42
    POSITIVE LOGITS
    Mel
    10.51
     Mel
    9.73
    mel
    8.45
     mel
    7.56
     Melody
    6.26
     Melissa
    6.10
     Melvin
    6.07
     Mell
    5.68
     Melanie
    5.48
    melon
    5.22
    Activations Density 0.006%

    No Known Activations