© 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. 10-ATT-KK
    11. 14823
    Prev
    Next
    INDEX
    Explanations

    the letter "D"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.09
    2:0.08
    3:0.08
    4:0.07
    5:0.07
    6:0.08
    7:0.09
    8:0.07
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
     SEN
    -2.73
    ander
    -2.69
    nor
    -2.68
     NOR
    -2.65
    enson
    -2.61
    DIT
    -2.60
     CONTR
    -2.49
    elsen
    -2.49
     Residents
    -2.46
    mit
    -2.45
    POSITIVE LOGITS
    ��
    3.68
     gelatin
    2.75
    enza
    2.73
     assum
    2.57
     shaved
    2.48
    isine
    2.48
     magically
    2.44
     cout
    2.38
    agascar
    2.38
     Incarnation
    2.30
    Activations Density 0.000%

    No Known Activations