© 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. 20559
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" and related forms of emphasis or punctuation in the text

    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
    1:0.06
    2:0.06
    3:0.06
    4:0.06
    5:0.06
    6:0.18
    7:0.06
    8:0.09
    9:0.15
    10:0.06
    11:0.05
    Negative Logits
     vm
    -3.51
     McCl
    -3.47
     Kro
    -3.42
     module
    -3.33
    kt
    -3.30
    Py
    -3.24
     Pok
    -3.20
     MH
    -3.12
    opath
    -3.06
     socket
    -3.04
    POSITIVE LOGITS
     Ariel
    9.41
    riel
    4.64
     Aram
    4.20
    abor
    4.02
     Uriel
    3.99
     Ezra
    3.88
     Corona
    3.85
    Cruz
    3.67
     Bland
    3.55
     Metatron
    3.55
    Activations Density 0.000%

    No Known Activations