© 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. 10-ATT-KK
    6. 14778
    Prev
    Next
    INDEX
    Explanations

    terms related to business management and societal structures

    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
    0:0.02
    1:0.03
    2:0.03
    3:0.05
    4:0.12
    5:0.14
    6:0.03
    7:0.05
    8:0.02
    9:0.37
    10:0.02
    11:0.08
    Negative Logits
     worthless
    -2.58
     pleading
    -2.41
     thanking
    -2.38
    ername
    -2.34
     {}
    -2.33
     cheerful
    -2.33
     worth
    -2.22
     {:
    -2.21
     disappointment
    -2.16
     murderer
    -2.12
    POSITIVE LOGITS
     interacted
    3.42
    different
    3.13
     interact
    3.12
     tweaked
    3.06
     intertwined
    2.96
     influenced
    2.96
     evolve
    2.91
    ociated
    2.84
     interacts
    2.76
     differed
    2.75
    Activations Density 0.098%

    No Known Activations