© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    instances of numbers and other specific attributes within comic and graphic content contexts

    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
    1:0.02
    2:0.05
    3:0.14
    4:0.03
    5:0.05
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.46
    11:0.03
    Negative Logits
     lifestyles
    -2.32
     flexibility
    -2.04
     tighter
    -2.01
     perpetually
    -1.91
     constantly
    -1.91
     perpetual
    -1.89
    Keeping
    -1.88
     extremes
    -1.87
     prolong
    -1.86
    Alternatively
    -1.85
    POSITIVE LOGITS
     debuted
    2.83
     premiered
    2.82
     began
    2.64
     occurred
    2.51
    arthed
    2.44
     came
    2.43
     launched
    2.41
     arrived
    2.39
     sprang
    2.38
    ��
    2.31
    Activations Density 0.186%

    No Known Activations