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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3109
    Prev
    Next
    INDEX
    Explanations

    conjunctions that link clauses or phrases within 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
    0:0.09
    1:0.07
    2:0.07
    3:0.08
    4:0.08
    5:0.09
    6:0.08
    7:0.08
    8:0.09
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     nep
    -3.25
    BuyableInstoreAndOnline
    -2.93
     perfume
    -2.81
     bec
    -2.79
     moon
    -2.75
     amber
    -2.74
     murd
    -2.68
     sailors
    -2.64
     ale
    -2.63
    bryce
    -2.59
    POSITIVE LOGITS
    cept
    2.83
    urance
    2.70
     Domin
    2.64
     Tat
    2.57
    olate
    2.53
    ensable
    2.51
     Expression
    2.50
     Relief
    2.49
     Fighting
    2.49
    abases
    2.49
    Activations Density 0.000%

    No Known Activations