Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18675
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks that signify the end of sentences

    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
    0:0.10
    1:0.03
    2:0.08
    3:0.02
    4:0.06
    5:0.04
    6:0.22
    7:0.06
    8:0.10
    9:0.20
    10:0.02
    11:0.03
    Negative Logits
     mattress
    -3.65
    ant
    -3.48
    ett
    -3.41
    etsy
    -3.41
    cffffcc
    -3.40
    ORD
    -3.38
     ├
    -3.36
     SPD
    -3.33
    ape
    -3.31
    ANT
    -3.31
    POSITIVE LOGITS
     Gol
    11.16
     gol
    5.88
     Gon
    4.75
     Kol
    4.41
     Garcia
    4.22
     Alvarez
    4.16
     Gro
    4.15
     Gi
    4.14
     Gors
    4.13
     Gul
    4.07
    Activations Density 0.000%

    No Known Activations