© 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. 10760
    Prev
    Next
    INDEX
    Explanations

    the use of prepositions

    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
    0:0.07
    1:0.08
    2:0.09
    3:0.08
    4:0.07
    5:0.09
    6:0.09
    7:0.07
    8:0.08
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     Gallagher
    -2.77
     Decker
    -2.48
    itol
    -2.33
    Gall
    -2.31
     Gonz
    -2.30
     Cheese
    -2.28
    aste
    -2.23
     Roma
    -2.22
     Redskins
    -2.21
     Bundy
    -2.21
    POSITIVE LOGITS
    覚醒
    3.40
    sung
    3.20
    三
    2.81
    ombies
    2.74
     裏�
    2.63
    */(
    2.50
    ##
    2.47
    ynes
    2.46
    %%%%
    2.45
    �
    2.41
    Activations Density 0.000%

    No Known Activations