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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14534
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and" as well as other connective phrases

    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
    0:0.06
    1:0.07
    2:0.07
    3:0.16
    4:0.14
    5:0.03
    6:0.05
    7:0.10
    8:0.04
    9:0.06
    10:0.05
    11:0.11
    Negative Logits
     PST
    -2.23
    icz
    -1.99
     outlook
    -1.97
     adjustments
    -1.96
     ›
    -1.85
     �
    -1.83
     changes
    -1.83
     fixation
    -1.83
     TODAY
    -1.82
     IST
    -1.82
    POSITIVE LOGITS
    ailable
    2.26
     srfAttach
    2.20
    ��
    2.11
    quished
    2.10
    ailability
    2.08
    anamo
    2.06
    Evidence
    2.06
     exting
    2.06
    engeance
    2.06
    ��極
    2.01
    Activations Density 0.001%

    No Known Activations